SlideShare uma empresa Scribd logo
1 de 9
Baixar para ler offline
Jan Zizka (Eds) : CCSIT, SIPP, AISC, PDCTA - 2013
pp. 421–429, 2013. © CS & IT-CSCP 2013 DOI : 10.5121/csit.2013.3648
CONTEXTUAL MODEL OF RECOMMENDING
RESOURCES ON AN ACADEMIC NETWORKING
PORTAL
Anoop Kumar Pandey, Amit Kumar and Balaji Rajendran
Centre for Development of Advanced Computing,
Electronics City, Bangalore
{anoop, amit, balaji}@cdac.in
ABSTRACT
Artificial Intelligence techniques have been instrumental in helping users to handle the large
amount of information on the Internet. The idea of recommendation systems, custom search
engines, and intelligent software has been widely accepted among users who seek assistance in
searching, sorting, classifying, filtering and sharing this vast quantity of information. In this
paper, we present a contextual model of recommendation engine which keeping in mind the
context and activities of a user, recommends resources in an academic networking portal. The
proposed method uses the implicit method of feedback and the concepts relationship hierarchy
to determine the similarity between a user and the resources in the portal. The proposed
algorithm has been tested on an academic networking portal and the results are convincing.
KEYWORDS
Contextual Model, Recommendation Engine, Academic Networking
1. INTRODUCTION
The development of World Wide Web has contributed to a ever growing global society of internet
users across the world. With exponential increase in users and thereby formation of avalanche of
information, It has been quite difficult to segregate the information we actually need from
amongst the mountain of web information. With need of a system for searching, sorting, filtering
and sharing relevant information out of the information overload, several personalized search
engines, recommender systems and intelligent software have been developed. A combination of
modeling the preferences of particular users, building content models, and modeling social
patterns in intelligent agents (Maes 1994) would provide users with a means for managing
information in a rational way, thus helping them to overcome the overwhelming information
content.
Recommender Systems or Recommendation Systems are quite common and used in several
applications. They primarily identify interesting information for a given user such as their likely
taste for a type of music, book, or movie or the most likely kind of people or groups whom they
would want to be associated with. , The common approaches adopted by these systems are:
Content-based filtering that use characteristics of an item or Collaborative filtering that rely on a
use’s profile and their social network [4]. Some examples are:
422 Computer Science & Information Technology (CS & IT)
• When viewing a product on Amazon, the store will recommend additional items based on
a matrix of what other shoppers bought along with the currently selected item.[8]
• Friends suggestion on Facebook.[6]
• People, group, job suggestion on LinkedIn.[7]
• Follow suggestions on Twitter.[9]
Figure 1. Examples of various recommendations from social media
In a relatively short time, several recommender agents have been developed and there is a
wide variety of such systems, all of which exploit a particular set of AI techniques.
Recommender systems typically produce a list of recommendations in one of the three main
information filtering methods: demographic, content based and collaborative [1]. Demo
graphic filtering approaches us e descriptions of people to learn the relationship between a
single item and the type of people who like it. Content -based filtering approaches
recommend items for the user based on the descriptions of previously evaluated items.
The collaborative filtering technique matches people with similar interests and then makes
recommendations on this basis. Another approach to overcome the shortcomings of collaborative
and content based filtering is Hybrid systems that exploit features of content-based and
collaborative filtering, since they will almost certainly prove to be complementary. Each
type of system has its own strengths and weaknesses.
The proposed algorithm of recommender system exploits user profile, implicit feedback and
explicitly cited interests. The algorithm uses a concept hierarchy, that holds all the concepts used
in the domain, which will be used to determine the context of the user and the resources to be
recommended, having similarity with user's interest.
The rest of this paper is organized as follows. Section 2 discusses some of the recommendation
techniques used in recommender agents in general and in academic environments. Section 3
details the proposed recommendation system for academic portals. Section 4 discusses the impact
of our proposed algorithm and results and section 5 concludes the paper.
Computer Science & Information Technology (CS & IT) 423
2. RELATED WORKS
In this section we briefly present some of the research literature review related to
recommender systems in general, academic recommendation system, and evaluation of
recommender systems.
Recommender systems typically produce a list of recommendations using one of the four main
information filtering methods [10]: demographic filtering, collaborative filtering, content-based
filtering, and hybrid methods. First, demographic filtering approaches use descriptions of
people to learn the relationship between a single item and the type of people who like it.
Collaborative filtering uses user-item rating matrix for predicting unseen preferences [11,
12]. It can be categorized into memory -based CF, which contains the whole matrix on memory,
and model-based CF, that involves building a model for estimation [13]. The most effective
memory-based algorithms known so far is item-based CF [19]. Matrix factorization, a kind of
model-based approach, known to be most efficient and accurate, especially after this approach
won the Netflix prize in 2009, is being used in many recent works [14, 16, 18, 17, 20]. Content-
based filtering, on the other hand, recommends items based on their characteristics as well as
based on previous evaluations of a user [10]. Pazzani et al. [15] studied this approach in depth,
including how to build user and item profiles. Hybrid approach, tries to combine both
collaborative and content-based recommendation. Koren [21] suggested effectively combining
rating information and user, item profiles for more accurate recommendation.
In [2], we used the contextual method of detecting relevant content for a user using a concept
hierarchy and concept extraction method. In [22] the authors had defined similarity between two
research papers based on the text similarity between them and then proposed their recommender
system developed using collaborative filtering methods.
AACORN [23], a course recommendation system that uses the course histories as the basis for
course advising. By reusing the experience embodied in historical student's transcripts, AACORN
can make reasonable suggestions with a limited amount of domain knowledge. The system uses
the edit distance between two course histories, as well as other heuristics to determine the
similarity between course histories.
3. CONTEXTUAL METHOD OF RECOMMENDATION
The Contextual Model of Recommendation System is built into a system that recommends
different resources viz. institutions, courses, events, projects, topic, and persons to ‘Follow’ and
get updates, to the various users of our academic networking portal. The users could be. students,
faculties, researchers, representatives of institutions etc, whose sole aim is to discover and share
information about their subjects of interest, information about institutions, courses, events,
projects, questionnaires, and such related activities for learning and research. In this pursuit, they
would like to receive regular updates regarding their favourite courses, persons, topics and
important notifications regarding events like seminars, conference and workshop etc. For this
purpose they “Follow” particular resource in which they are interested in. While there are
thousands of resources on the academic portal, it is a tedious job to search out resources of own
interest and check the latest updates. The criticality of recommendation system will guide the user
to sift through such large information by recommending them the appropriate resources based on
their profile, their explicit and implicit feedback.
We start by defining the common terms that are used in our system, following it with the
recommendation algorithm.
424 Computer Science & Information Technology (CS & IT)
3.1. Definitions
Resource: All components of our academic networking website are treated as resources.
Examples may include institutes, faculties, courses, events, projects, web links, topics etc. Our
recommendation system recommends these resources to the user to ‘Follow’.
Concepts & Relationships: Concept in general, could refer to all the terminologies and
vocabulary of a particular domain which is used to describe it. The definition of concepts and
relationship between the concepts is typically captured in the form of ontology for a domain. We
use a simple structure called concept tree that captures two kinds of relationships: is-a and is-in.
For instance in the statement, “Java is an Object-oriented language”, the concepts ‘Java’ and
’object-oriented language’ are captured using ‘is-a’ relationship. The is-in relationship is captured
as a composition tree. For instance, “Object-oriented Languages” is contained within the concept
of “Programming Languages”.
N.B.: All resources are concepts.
Concept Extraction: It is the process of extracting the concepts in a given piece of text, by
comparing the main terms with the concept tree.
Co-occurrence Pattern: It defines the pattern and frequency of a concept occurring with another
concept within a defined window. E.g. Sachin and Cricket co-occurs with each other often.
Follow List: Resources, a user is already watching.
Posts: Informative content posted on a resource’s wall/timeline.
Cosine Similarity: Cosine similarity is a measure of similarity between two vectors by
measuring the cosine of the angle between them. The cosine of the angle between two vectors
thus determines whether two vectors are pointing in roughly the same direction.
3.2. Steps towards Algorithm
In the proposed recommendation algorithm, we use three parameters – User’s Profile, User’s
Follow List, and User’s Navigation History as input to our algorithm for determining the likely
list of resources that a user would be interested in. A factor of weight has been given to each of
these parameters so that the results are not skewed to a single parameter. They are assigned as
high for explicit and low for implicit parameters.
The user profile will explicitly contain the user’s skill-set, experience and areas of interest. The
user’s follow list indicates the resources that the user is interested in getting the recent updates of
that particular resource. The user’s navigation history is an implicit parameter that reveals the
interests of the user.
When we have a set of resources, the user is interested in, concepts are extracted from them
through contextual method and then we try to find out if some other resource also belong to or
matches with the same pool of resources. If we find resources in that pool which the user is
currently unaware of, then they are recommended to the user. The recommendations are
generated dynamically – i.e., on the live and changing data.
Computer Science & Information Technology (CS & IT) 425
3.3. Algorithm for recommendation generation
Assumptions: a) Presence of concept extraction algorithm.
b) Presence of concept and containment trees.
c) Resource R has been properly modeled.
d) Presence of Co-occurrence table based on descriptions of concepts. Input: User’s
Profile, User’s Follow List, User’s Navigation Pattern. Output: Set of recommendation
comprising 3 resources.
Algorithm:
Extract the concepts from User Profile Columns: “Skill-Set”, “Experience”, “Area of
Interest”. Store it in an associative array CUP with key as concept-id and value as term
frequency of occurrence.
Extract the concepts from user’s Follow list and store it in an array CFL with
corresponding term frequency.
Extract the concepts from user’s navigation list and store it in an array CNL with
corresponding term frequency.
Combine the array in one array with different weightages.
C = 3*CUP + 2*CFL + 0.25*CNL
Expand the concept-list C based on co-occurrence table and update the frequency as well.
CEX = C U (Concepts co-occurring with C).
Create Weight vector of length ‘n’, where n is the total no of concepts in CEX.
= [wi] where wi is the weightage or term frequency of concepts within CEX
Represent each resource as a vector , which the user is not watching, in terms of the
concepts in CEX and their corresponding term frequency in the resource description and
the posts on the resource’s wall in last one year.
For each resource calculate cosine similarity (Cosim) with concept vector representing
the user interest as:
Cosim ( ) = . /
Arrange the resources in decreasing order of cosine similarity value.
Filter out top ‘u’ resources as per following rule:
= 0.8 *
Find out top u resources and recommend any 3 out of them.
4. IMPLEMENTATION AND RESULTS
An academic networking portal [27], with interactive features for its users was used for validating
our approach. The website features the recommendation system with facility to hover over
recommendation to watch information, click to navigate to the resource page and Follow button
to accept recommendation. Figure 2 and 3 illustrate the recommendation and hover function. We
captured each action (hover, click and Follow) corresponding to a particular recommended
resource while user was presented with three recommendations on a page. These actions were
treated as metrics for evaluation in addition to manual inspection, where the recommended
resources were checked to whether having the similarity with user's interest and trend.
426 Computer Science & Information Technology (CS & IT)
Figure 2. Screenshot of recommendation of resources (institutions and person)
Figure 3. Examples of various recommendations with hover effect.
In manual inspection, the results were pretty impressive with recommended resources amounting
to 85-90% similarity with user's interest. The test was conducted with 70 user's profile matching
with recommended resources.
The recommendation system was also tested from user's perspective and in terms of
effectiveness/usefulness of the recommendation. Corresponding to a user, for each set of
recommendations, user's actions viz. 'Click', 'Hover', and 'Watch' were captured. The data
collected was analysed to check how recommended resources had been considered useful. Table 1
describes the total recommendations received by each user and the summary of actions taken by
the users:
Computer Science & Information Technology (CS & IT) 427
Table 1 Statistics of various actions to check effectiveness of the proposed solution.
User/Action Total
Recommendations
Hover Click Watch
U1 15 14(93.3%) 12(80%) 9(60%)
U2 24 21(87.5%) 19(79.2%) 17(70.8%)
U3 18 16(88.9%) 13(72.2%) 11(61.1%)
U4 12 12(100%) 11(91.7%) 9(75%)
U5 33 31(93.9%) 28(84.8%) 24(72.7%)
U6 9 9(100%) 9(100%) 6(66.7%)
-
-
Total 966 907(93.9%) 788(81.6%) 693(71.7%)
The results were quite impressive as majority of the presented recommendations 94% were
hovered for information display, 82% were clicked to view full information and 72% were
accepted for following. Considering the action taken by the user in terms of their „Following‟ a
resource, the results are quite impressive.
5. CONCLUSIONS
In this paper, we have presented a Contextual Model of Resource Recommendation System for
academic portals, which recommends different resources viz. Institution, course, project, topic,
event and academician to the users of the portal. The proposed system determines the concepts
and cosine similarity between them with understanding of context and identifies potential
resources to be recommended to the user based on user's profile and their explicit as well as
implicit feedbacks. Evaluation results show the utility of our proposed system. We made the
assumption that the resources in the system have been well defined and modeled. We also
assumed the existence of ontology in terms of concept tree with simple relationships that defines
the domain in which the academic portal operates. This methodology could be easily extended to
other domain-specific vertical portals, though the challenge would be in extending it to a generic
and interactive information system.
REFERENCES
[1] Miquel Montaner, Beatriz Lopez and Josep Lluis De La Rosa: A Taxonomy of Recommender Agents
on the Internet Artificial Intelligence Review 19: 285–330, 2003.
[2] Balaji Rajendran and Anoop Kumar Pandey, “Contextual Strategies for Detecting Spam in Academic
Portals”, The 2nd International Conference on Computer Science and Information Technology
(CCSIT-2012), Royal Orchid Central, Bangalore, January 2-4, 2012.
[3] Jennings, A. & Higuchi, H. (1993). A User Model Neural Network for a Personal News Service. User
Modeling and User-Adapted Interaction 3: 1–25.
[4] Recommender Systems, http://en.wikipedia.org/wiki/Recommender_system
[5] Morita, M. & Shinoda, Y. (1994). Information Filtering Based on User Behaviour Analysis and Best
Match Text Retrieval. In Proceedings of SIGIR‟94, 272–81. Dublin, Ireland: Springer-Verlag.
[6] Facebook, http://www.facebook.com
[7] LinkedIn, http://www.linkedin.com
[8] Amazon, http://www.amazon.com
[9] Twitter, http://www.twitter.com
428 Computer Science & Information Technology (CS & IT)
[10] D. Jannach, M. Zanker, A. Felfernig, and G. Friedrich. Recommender Systems. An Introduction.
Cambridge, 2011.
[11] X. Su and T. M. Khoshgoftaar. A survey of collaborative filtering techniques. Adv. in Artif. Intell,
2009:4:2.4:2, January 2009.
[12] G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of
the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Enginerring,
17(6):734.749, 2005.
[13] J. S. Breese, D. Heckerman, and C. Kadie. Empirical analysis of predictive algorithms for
collaborative filtering. pages 43.52. Morgan Kaufmann, 1998.
[14] A. Paterek. Improving regularized singular value decomposition for collaborative filtering. Statistics,
2007:2.5.
[15] M. Pazzani and D. Billsus. Content-based recommendation systems. In P. Brusilovsky, A. Kobsa, and
W. Nejdl, editors, The Adaptive Web, volume 4321 of Lecture Notes in Computer Science, pages
325.341. Springer Berlin, Heidelberg, 2007.
[16] J. D. M. Rennie and N. Srebro. Fast maximum margin matrix factorization for collaborative
prediction. In Proceedings of the 22nd international conference on Machine learning, ICML .05,
pages 713.719, New York, NY, USA, 2005. ACM.
[17] L. D. D. Algorithms for nonnegative matrix factorization. Advances in Neural Information Processing
Systems, 13:556.562, 2001.
[18] R. Salakhutdinov and A. Mnih. Probabilistic matrix factorization. 2008.
[19] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Item-based collaborative filtering recommendation
algorithms. Pages 285.295, 2001.
[20] K. Yu, S. Zhu, J. Lafferty, and Y. Gong. Fast nonparametric matrix factorization for large-scale
collaborative filtering. In Proceedings of the 32nd international ACM SIGIR conference on Research
and development in information retrieval, SIGIR .09, pages 211.218, New York, NY, USA, 2009.
ACM.
[21] Y. Koren. Factorization meets the neighborhood: a multifaceted collaborative filtering model. In
Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data
mining, KDD ‟08, pages 426–434, New York, NY, USA, 2008. ACM.
[22] Joonseok Lee, Kisung Lee, Jennifer G. Kim: Personalized Academic Research Paper
Recommendation System, http://www.cc.gatech.edu/~jkim693/ projects / recommendation.pdf,
Georgia Institute of Technology, Atlanta, GA.
[23] JJ Sandvig, Robin Burke: AACORN: A CBR Recommender for Academic Advising,
http://facweb.cti.depaul.edu/research/techreports/TR05-015.doc
[24] K. Sugiyama and M.-Y. Kan. Scholarly paper recommendation via user‟s recent research interests. In
Proceedings of the 10th annual joint conference on Digital libraries, JCDL ‟10, pages 29–38, New
York, NY, USA, 2010. ACM.
[25] Tang and J. Zhang. A discriminative approach to topic-based citation recommendation. In T.
Theeramunkong, B. Kijsirikul, N. Cercone, and T.-B. Ho, editors, Advances in Knowledge Discovery
and Data Mining, volume 5476 of Lecture Notes in Computer Science, pages 572–579. Springer
Berlin / Heidelberg, 2009.
[26] K. Yu, S. Zhu, J. Lafferty, and Y. Gong. Fast nonparametric matrix factorization for large-scale
collaborative filtering. In Proceedings of the 32nd international ACM SIGIR conference on Research
and development in information retrieval, SIGIR ‟09, pages 211–218, New York, NY, USA, 2009.
ACM.
[27] Seekha, http://www.seekha.in
Computer Science & Information Technology (CS & IT) 429
Authors
Anoop Kumar Pandey
Mr Anoop Kumar Pandey holds a B. Tech degree in CSE graduate (2010) from Shri
Mata Vaishno Devi University, Jammu. He was a Chancellor Gold Medalist. He joined
C-DAC after the college and currently working here as a Technical Officer. He is also
pursuing MS by Research from IIIT Bangalore, India.
Amit Kumar
Mr Amit Kumar completed his B.Tech in CSE, from Biju Patnaik University of
Technology (BPUT), Orissa. He currently works as a Project Engineer at CDAC since
2011. His current work of area is web application developmentt and Disaster Recovery
site management and maintenance. His interest area includes web-design, database
management system, and information security.
Dr Balaji Rajendran
Dr Balaji Rajendran holds a Ph.D degree from Madurai Kamaraj University and is
currently working as a Senior Technical officer at CDAC Bangalore. He has 11+ years of
experience in teaching and R&D. His interest area and domain expertise include
information security, web information systems, social media and intelligence.

Mais conteúdo relacionado

Mais procurados

A Review: Text Classification on Social Media Data
A Review: Text Classification on Social Media DataA Review: Text Classification on Social Media Data
A Review: Text Classification on Social Media DataIOSR Journals
 
IRJET- Analysis on Existing Methodologies of User Service Rating Prediction S...
IRJET- Analysis on Existing Methodologies of User Service Rating Prediction S...IRJET- Analysis on Existing Methodologies of User Service Rating Prediction S...
IRJET- Analysis on Existing Methodologies of User Service Rating Prediction S...IRJET Journal
 
Recommender Systems
Recommender SystemsRecommender Systems
Recommender Systemsvivatechijri
 
A Survey on Decision Support Systems in Social Media
A Survey on Decision Support Systems in Social MediaA Survey on Decision Support Systems in Social Media
A Survey on Decision Support Systems in Social MediaEditor IJCATR
 
Enhanced User-driven Ranking System with Splay Tree
Enhanced User-driven Ranking System with Splay TreeEnhanced User-driven Ranking System with Splay Tree
Enhanced User-driven Ranking System with Splay TreeTELKOMNIKA JOURNAL
 
Scaling Down Dimensions and Feature Extraction in Document Repository Classif...
Scaling Down Dimensions and Feature Extraction in Document Repository Classif...Scaling Down Dimensions and Feature Extraction in Document Repository Classif...
Scaling Down Dimensions and Feature Extraction in Document Repository Classif...ijdmtaiir
 
A Novel Approach for Travel Package Recommendation Using Probabilistic Matrix...
A Novel Approach for Travel Package Recommendation Using Probabilistic Matrix...A Novel Approach for Travel Package Recommendation Using Probabilistic Matrix...
A Novel Approach for Travel Package Recommendation Using Probabilistic Matrix...IJSRD
 
IRJET- A Survey on Recommender Systems used for User Service Rating in Social...
IRJET- A Survey on Recommender Systems used for User Service Rating in Social...IRJET- A Survey on Recommender Systems used for User Service Rating in Social...
IRJET- A Survey on Recommender Systems used for User Service Rating in Social...IRJET Journal
 
A literature survey on recommendation
A literature survey on recommendationA literature survey on recommendation
A literature survey on recommendationaciijournal
 
Using content features to enhance the
Using content features to enhance theUsing content features to enhance the
Using content features to enhance theijaia
 
Cluster Based Web Search Using Support Vector Machine
Cluster Based Web Search Using Support Vector MachineCluster Based Web Search Using Support Vector Machine
Cluster Based Web Search Using Support Vector MachineCSCJournals
 

Mais procurados (15)

A Review: Text Classification on Social Media Data
A Review: Text Classification on Social Media DataA Review: Text Classification on Social Media Data
A Review: Text Classification on Social Media Data
 
IRJET- Analysis on Existing Methodologies of User Service Rating Prediction S...
IRJET- Analysis on Existing Methodologies of User Service Rating Prediction S...IRJET- Analysis on Existing Methodologies of User Service Rating Prediction S...
IRJET- Analysis on Existing Methodologies of User Service Rating Prediction S...
 
Recommender Systems
Recommender SystemsRecommender Systems
Recommender Systems
 
A Survey on Decision Support Systems in Social Media
A Survey on Decision Support Systems in Social MediaA Survey on Decision Support Systems in Social Media
A Survey on Decision Support Systems in Social Media
 
Enhanced User-driven Ranking System with Splay Tree
Enhanced User-driven Ranking System with Splay TreeEnhanced User-driven Ranking System with Splay Tree
Enhanced User-driven Ranking System with Splay Tree
 
Scaling Down Dimensions and Feature Extraction in Document Repository Classif...
Scaling Down Dimensions and Feature Extraction in Document Repository Classif...Scaling Down Dimensions and Feature Extraction in Document Repository Classif...
Scaling Down Dimensions and Feature Extraction in Document Repository Classif...
 
243
243243
243
 
A Novel Approach for Travel Package Recommendation Using Probabilistic Matrix...
A Novel Approach for Travel Package Recommendation Using Probabilistic Matrix...A Novel Approach for Travel Package Recommendation Using Probabilistic Matrix...
A Novel Approach for Travel Package Recommendation Using Probabilistic Matrix...
 
IRJET- A Survey on Recommender Systems used for User Service Rating in Social...
IRJET- A Survey on Recommender Systems used for User Service Rating in Social...IRJET- A Survey on Recommender Systems used for User Service Rating in Social...
IRJET- A Survey on Recommender Systems used for User Service Rating in Social...
 
A literature survey on recommendation
A literature survey on recommendationA literature survey on recommendation
A literature survey on recommendation
 
B1802021823
B1802021823B1802021823
B1802021823
 
Using content features to enhance the
Using content features to enhance theUsing content features to enhance the
Using content features to enhance the
 
At4102337341
At4102337341At4102337341
At4102337341
 
K1803057782
K1803057782K1803057782
K1803057782
 
Cluster Based Web Search Using Support Vector Machine
Cluster Based Web Search Using Support Vector MachineCluster Based Web Search Using Support Vector Machine
Cluster Based Web Search Using Support Vector Machine
 

Semelhante a Contextual Model Recommends Academic Resources

A Literature Survey on Recommendation Systems for Scientific Articles.pdf
A Literature Survey on Recommendation Systems for Scientific Articles.pdfA Literature Survey on Recommendation Systems for Scientific Articles.pdf
A Literature Survey on Recommendation Systems for Scientific Articles.pdfAmber Ford
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)IJERD Editor
 
Recommendation System Using Social Networking
Recommendation System Using Social Networking Recommendation System Using Social Networking
Recommendation System Using Social Networking ijcseit
 
A Literature Survey on Recommendation System Based on Sentimental Analysis
A Literature Survey on Recommendation System Based on Sentimental AnalysisA Literature Survey on Recommendation System Based on Sentimental Analysis
A Literature Survey on Recommendation System Based on Sentimental Analysisaciijournal
 
A Study of Neural Network Learning-Based Recommender System
A Study of Neural Network Learning-Based Recommender SystemA Study of Neural Network Learning-Based Recommender System
A Study of Neural Network Learning-Based Recommender Systemtheijes
 
AN EXTENDED HYBRID RECOMMENDER SYSTEM BASED ON ASSOCIATION RULES MINING IN DI...
AN EXTENDED HYBRID RECOMMENDER SYSTEM BASED ON ASSOCIATION RULES MINING IN DI...AN EXTENDED HYBRID RECOMMENDER SYSTEM BASED ON ASSOCIATION RULES MINING IN DI...
AN EXTENDED HYBRID RECOMMENDER SYSTEM BASED ON ASSOCIATION RULES MINING IN DI...cscpconf
 
A LOCATION-BASED RECOMMENDER SYSTEM FRAMEWORK TO IMPROVE ACCURACY IN USERBASE...
A LOCATION-BASED RECOMMENDER SYSTEM FRAMEWORK TO IMPROVE ACCURACY IN USERBASE...A LOCATION-BASED RECOMMENDER SYSTEM FRAMEWORK TO IMPROVE ACCURACY IN USERBASE...
A LOCATION-BASED RECOMMENDER SYSTEM FRAMEWORK TO IMPROVE ACCURACY IN USERBASE...ijcsa
 
Information Filtration
Information FiltrationInformation Filtration
Information FiltrationAli Jafar
 
A Social Network-Empowered Research Analytics Framework For Project Selection
A Social Network-Empowered Research Analytics Framework For Project SelectionA Social Network-Empowered Research Analytics Framework For Project Selection
A Social Network-Empowered Research Analytics Framework For Project SelectionNat Rice
 
A Comprehensive Review of Relevant Techniques used in Course Recommendation S...
A Comprehensive Review of Relevant Techniques used in Course Recommendation S...A Comprehensive Review of Relevant Techniques used in Course Recommendation S...
A Comprehensive Review of Relevant Techniques used in Course Recommendation S...IRJET Journal
 
Recommendation system (1).pptx
Recommendation system (1).pptxRecommendation system (1).pptx
Recommendation system (1).pptxprathammishra28
 
recommendationsystem1-221109055232-c8b46131.pdf
recommendationsystem1-221109055232-c8b46131.pdfrecommendationsystem1-221109055232-c8b46131.pdf
recommendationsystem1-221109055232-c8b46131.pdf13DikshaDatir
 
SIMILARITY MEASURES FOR RECOMMENDER SYSTEMS: A COMPARATIVE STUDY
SIMILARITY MEASURES FOR RECOMMENDER SYSTEMS: A COMPARATIVE STUDYSIMILARITY MEASURES FOR RECOMMENDER SYSTEMS: A COMPARATIVE STUDY
SIMILARITY MEASURES FOR RECOMMENDER SYSTEMS: A COMPARATIVE STUDYJournal For Research
 
FHCC: A SOFT HIERARCHICAL CLUSTERING APPROACH FOR COLLABORATIVE FILTERING REC...
FHCC: A SOFT HIERARCHICAL CLUSTERING APPROACH FOR COLLABORATIVE FILTERING REC...FHCC: A SOFT HIERARCHICAL CLUSTERING APPROACH FOR COLLABORATIVE FILTERING REC...
FHCC: A SOFT HIERARCHICAL CLUSTERING APPROACH FOR COLLABORATIVE FILTERING REC...IJDKP
 
FIND MY VENUE: Content & Review Based Location Recommendation System
FIND MY VENUE: Content & Review Based Location Recommendation SystemFIND MY VENUE: Content & Review Based Location Recommendation System
FIND MY VENUE: Content & Review Based Location Recommendation SystemIJTET Journal
 
A Citation-Based Recommender System For Scholarly Paper Recommendation
A Citation-Based Recommender System For Scholarly Paper RecommendationA Citation-Based Recommender System For Scholarly Paper Recommendation
A Citation-Based Recommender System For Scholarly Paper RecommendationDaniel Wachtel
 
Ontological and clustering approach for content based recommendation systems
Ontological and clustering approach for content based recommendation systemsOntological and clustering approach for content based recommendation systems
Ontological and clustering approach for content based recommendation systemsvikramadityajakkula
 
Integrated expert recommendation model for online communitiesst02
Integrated expert recommendation model for online communitiesst02Integrated expert recommendation model for online communitiesst02
Integrated expert recommendation model for online communitiesst02IJwest
 

Semelhante a Contextual Model Recommends Academic Resources (20)

lms final ppt.pptx
lms final ppt.pptxlms final ppt.pptx
lms final ppt.pptx
 
A Literature Survey on Recommendation Systems for Scientific Articles.pdf
A Literature Survey on Recommendation Systems for Scientific Articles.pdfA Literature Survey on Recommendation Systems for Scientific Articles.pdf
A Literature Survey on Recommendation Systems for Scientific Articles.pdf
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
 
Recommendation System Using Social Networking
Recommendation System Using Social Networking Recommendation System Using Social Networking
Recommendation System Using Social Networking
 
A Literature Survey on Recommendation System Based on Sentimental Analysis
A Literature Survey on Recommendation System Based on Sentimental AnalysisA Literature Survey on Recommendation System Based on Sentimental Analysis
A Literature Survey on Recommendation System Based on Sentimental Analysis
 
A Study of Neural Network Learning-Based Recommender System
A Study of Neural Network Learning-Based Recommender SystemA Study of Neural Network Learning-Based Recommender System
A Study of Neural Network Learning-Based Recommender System
 
AN EXTENDED HYBRID RECOMMENDER SYSTEM BASED ON ASSOCIATION RULES MINING IN DI...
AN EXTENDED HYBRID RECOMMENDER SYSTEM BASED ON ASSOCIATION RULES MINING IN DI...AN EXTENDED HYBRID RECOMMENDER SYSTEM BASED ON ASSOCIATION RULES MINING IN DI...
AN EXTENDED HYBRID RECOMMENDER SYSTEM BASED ON ASSOCIATION RULES MINING IN DI...
 
A LOCATION-BASED RECOMMENDER SYSTEM FRAMEWORK TO IMPROVE ACCURACY IN USERBASE...
A LOCATION-BASED RECOMMENDER SYSTEM FRAMEWORK TO IMPROVE ACCURACY IN USERBASE...A LOCATION-BASED RECOMMENDER SYSTEM FRAMEWORK TO IMPROVE ACCURACY IN USERBASE...
A LOCATION-BASED RECOMMENDER SYSTEM FRAMEWORK TO IMPROVE ACCURACY IN USERBASE...
 
Information Filtration
Information FiltrationInformation Filtration
Information Filtration
 
AN EFFECTIVE FRAMEWORK FOR GENERATING RECOMMENDATIONS
AN EFFECTIVE FRAMEWORK FOR GENERATING RECOMMENDATIONSAN EFFECTIVE FRAMEWORK FOR GENERATING RECOMMENDATIONS
AN EFFECTIVE FRAMEWORK FOR GENERATING RECOMMENDATIONS
 
A Social Network-Empowered Research Analytics Framework For Project Selection
A Social Network-Empowered Research Analytics Framework For Project SelectionA Social Network-Empowered Research Analytics Framework For Project Selection
A Social Network-Empowered Research Analytics Framework For Project Selection
 
A Comprehensive Review of Relevant Techniques used in Course Recommendation S...
A Comprehensive Review of Relevant Techniques used in Course Recommendation S...A Comprehensive Review of Relevant Techniques used in Course Recommendation S...
A Comprehensive Review of Relevant Techniques used in Course Recommendation S...
 
Recommendation system (1).pptx
Recommendation system (1).pptxRecommendation system (1).pptx
Recommendation system (1).pptx
 
recommendationsystem1-221109055232-c8b46131.pdf
recommendationsystem1-221109055232-c8b46131.pdfrecommendationsystem1-221109055232-c8b46131.pdf
recommendationsystem1-221109055232-c8b46131.pdf
 
SIMILARITY MEASURES FOR RECOMMENDER SYSTEMS: A COMPARATIVE STUDY
SIMILARITY MEASURES FOR RECOMMENDER SYSTEMS: A COMPARATIVE STUDYSIMILARITY MEASURES FOR RECOMMENDER SYSTEMS: A COMPARATIVE STUDY
SIMILARITY MEASURES FOR RECOMMENDER SYSTEMS: A COMPARATIVE STUDY
 
FHCC: A SOFT HIERARCHICAL CLUSTERING APPROACH FOR COLLABORATIVE FILTERING REC...
FHCC: A SOFT HIERARCHICAL CLUSTERING APPROACH FOR COLLABORATIVE FILTERING REC...FHCC: A SOFT HIERARCHICAL CLUSTERING APPROACH FOR COLLABORATIVE FILTERING REC...
FHCC: A SOFT HIERARCHICAL CLUSTERING APPROACH FOR COLLABORATIVE FILTERING REC...
 
FIND MY VENUE: Content & Review Based Location Recommendation System
FIND MY VENUE: Content & Review Based Location Recommendation SystemFIND MY VENUE: Content & Review Based Location Recommendation System
FIND MY VENUE: Content & Review Based Location Recommendation System
 
A Citation-Based Recommender System For Scholarly Paper Recommendation
A Citation-Based Recommender System For Scholarly Paper RecommendationA Citation-Based Recommender System For Scholarly Paper Recommendation
A Citation-Based Recommender System For Scholarly Paper Recommendation
 
Ontological and clustering approach for content based recommendation systems
Ontological and clustering approach for content based recommendation systemsOntological and clustering approach for content based recommendation systems
Ontological and clustering approach for content based recommendation systems
 
Integrated expert recommendation model for online communitiesst02
Integrated expert recommendation model for online communitiesst02Integrated expert recommendation model for online communitiesst02
Integrated expert recommendation model for online communitiesst02
 

Mais de cscpconf

ANALYSIS OF LAND SURFACE DEFORMATION GRADIENT BY DINSAR
ANALYSIS OF LAND SURFACE DEFORMATION GRADIENT BY DINSAR ANALYSIS OF LAND SURFACE DEFORMATION GRADIENT BY DINSAR
ANALYSIS OF LAND SURFACE DEFORMATION GRADIENT BY DINSAR cscpconf
 
4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION
4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION
4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATIONcscpconf
 
MOVING FROM WATERFALL TO AGILE PROCESS IN SOFTWARE ENGINEERING CAPSTONE PROJE...
MOVING FROM WATERFALL TO AGILE PROCESS IN SOFTWARE ENGINEERING CAPSTONE PROJE...MOVING FROM WATERFALL TO AGILE PROCESS IN SOFTWARE ENGINEERING CAPSTONE PROJE...
MOVING FROM WATERFALL TO AGILE PROCESS IN SOFTWARE ENGINEERING CAPSTONE PROJE...cscpconf
 
PROMOTING STUDENT ENGAGEMENT USING SOCIAL MEDIA TECHNOLOGIES
PROMOTING STUDENT ENGAGEMENT USING SOCIAL MEDIA TECHNOLOGIESPROMOTING STUDENT ENGAGEMENT USING SOCIAL MEDIA TECHNOLOGIES
PROMOTING STUDENT ENGAGEMENT USING SOCIAL MEDIA TECHNOLOGIEScscpconf
 
A SURVEY ON QUESTION ANSWERING SYSTEMS: THE ADVANCES OF FUZZY LOGIC
A SURVEY ON QUESTION ANSWERING SYSTEMS: THE ADVANCES OF FUZZY LOGICA SURVEY ON QUESTION ANSWERING SYSTEMS: THE ADVANCES OF FUZZY LOGIC
A SURVEY ON QUESTION ANSWERING SYSTEMS: THE ADVANCES OF FUZZY LOGICcscpconf
 
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS cscpconf
 
INTELLIGENT ELECTRONIC ASSESSMENT FOR SUBJECTIVE EXAMS
INTELLIGENT ELECTRONIC ASSESSMENT FOR SUBJECTIVE EXAMS INTELLIGENT ELECTRONIC ASSESSMENT FOR SUBJECTIVE EXAMS
INTELLIGENT ELECTRONIC ASSESSMENT FOR SUBJECTIVE EXAMS cscpconf
 
TWO DISCRETE BINARY VERSIONS OF AFRICAN BUFFALO OPTIMIZATION METAHEURISTIC
TWO DISCRETE BINARY VERSIONS OF AFRICAN BUFFALO OPTIMIZATION METAHEURISTICTWO DISCRETE BINARY VERSIONS OF AFRICAN BUFFALO OPTIMIZATION METAHEURISTIC
TWO DISCRETE BINARY VERSIONS OF AFRICAN BUFFALO OPTIMIZATION METAHEURISTICcscpconf
 
DETECTION OF ALGORITHMICALLY GENERATED MALICIOUS DOMAIN
DETECTION OF ALGORITHMICALLY GENERATED MALICIOUS DOMAINDETECTION OF ALGORITHMICALLY GENERATED MALICIOUS DOMAIN
DETECTION OF ALGORITHMICALLY GENERATED MALICIOUS DOMAINcscpconf
 
GLOBAL MUSIC ASSET ASSURANCE DIGITAL CURRENCY: A DRM SOLUTION FOR STREAMING C...
GLOBAL MUSIC ASSET ASSURANCE DIGITAL CURRENCY: A DRM SOLUTION FOR STREAMING C...GLOBAL MUSIC ASSET ASSURANCE DIGITAL CURRENCY: A DRM SOLUTION FOR STREAMING C...
GLOBAL MUSIC ASSET ASSURANCE DIGITAL CURRENCY: A DRM SOLUTION FOR STREAMING C...cscpconf
 
IMPORTANCE OF VERB SUFFIX MAPPING IN DISCOURSE TRANSLATION SYSTEM
IMPORTANCE OF VERB SUFFIX MAPPING IN DISCOURSE TRANSLATION SYSTEMIMPORTANCE OF VERB SUFFIX MAPPING IN DISCOURSE TRANSLATION SYSTEM
IMPORTANCE OF VERB SUFFIX MAPPING IN DISCOURSE TRANSLATION SYSTEMcscpconf
 
EXACT SOLUTIONS OF A FAMILY OF HIGHER-DIMENSIONAL SPACE-TIME FRACTIONAL KDV-T...
EXACT SOLUTIONS OF A FAMILY OF HIGHER-DIMENSIONAL SPACE-TIME FRACTIONAL KDV-T...EXACT SOLUTIONS OF A FAMILY OF HIGHER-DIMENSIONAL SPACE-TIME FRACTIONAL KDV-T...
EXACT SOLUTIONS OF A FAMILY OF HIGHER-DIMENSIONAL SPACE-TIME FRACTIONAL KDV-T...cscpconf
 
AUTOMATED PENETRATION TESTING: AN OVERVIEW
AUTOMATED PENETRATION TESTING: AN OVERVIEWAUTOMATED PENETRATION TESTING: AN OVERVIEW
AUTOMATED PENETRATION TESTING: AN OVERVIEWcscpconf
 
CLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORK
CLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORKCLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORK
CLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORKcscpconf
 
VALIDATION METHOD OF FUZZY ASSOCIATION RULES BASED ON FUZZY FORMAL CONCEPT AN...
VALIDATION METHOD OF FUZZY ASSOCIATION RULES BASED ON FUZZY FORMAL CONCEPT AN...VALIDATION METHOD OF FUZZY ASSOCIATION RULES BASED ON FUZZY FORMAL CONCEPT AN...
VALIDATION METHOD OF FUZZY ASSOCIATION RULES BASED ON FUZZY FORMAL CONCEPT AN...cscpconf
 
PROBABILITY BASED CLUSTER EXPANSION OVERSAMPLING TECHNIQUE FOR IMBALANCED DATA
PROBABILITY BASED CLUSTER EXPANSION OVERSAMPLING TECHNIQUE FOR IMBALANCED DATAPROBABILITY BASED CLUSTER EXPANSION OVERSAMPLING TECHNIQUE FOR IMBALANCED DATA
PROBABILITY BASED CLUSTER EXPANSION OVERSAMPLING TECHNIQUE FOR IMBALANCED DATAcscpconf
 
CHARACTER AND IMAGE RECOGNITION FOR DATA CATALOGING IN ECOLOGICAL RESEARCH
CHARACTER AND IMAGE RECOGNITION FOR DATA CATALOGING IN ECOLOGICAL RESEARCHCHARACTER AND IMAGE RECOGNITION FOR DATA CATALOGING IN ECOLOGICAL RESEARCH
CHARACTER AND IMAGE RECOGNITION FOR DATA CATALOGING IN ECOLOGICAL RESEARCHcscpconf
 
SOCIAL MEDIA ANALYTICS FOR SENTIMENT ANALYSIS AND EVENT DETECTION IN SMART CI...
SOCIAL MEDIA ANALYTICS FOR SENTIMENT ANALYSIS AND EVENT DETECTION IN SMART CI...SOCIAL MEDIA ANALYTICS FOR SENTIMENT ANALYSIS AND EVENT DETECTION IN SMART CI...
SOCIAL MEDIA ANALYTICS FOR SENTIMENT ANALYSIS AND EVENT DETECTION IN SMART CI...cscpconf
 
SOCIAL NETWORK HATE SPEECH DETECTION FOR AMHARIC LANGUAGE
SOCIAL NETWORK HATE SPEECH DETECTION FOR AMHARIC LANGUAGESOCIAL NETWORK HATE SPEECH DETECTION FOR AMHARIC LANGUAGE
SOCIAL NETWORK HATE SPEECH DETECTION FOR AMHARIC LANGUAGEcscpconf
 
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXTGENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXTcscpconf
 

Mais de cscpconf (20)

ANALYSIS OF LAND SURFACE DEFORMATION GRADIENT BY DINSAR
ANALYSIS OF LAND SURFACE DEFORMATION GRADIENT BY DINSAR ANALYSIS OF LAND SURFACE DEFORMATION GRADIENT BY DINSAR
ANALYSIS OF LAND SURFACE DEFORMATION GRADIENT BY DINSAR
 
4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION
4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION
4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION
 
MOVING FROM WATERFALL TO AGILE PROCESS IN SOFTWARE ENGINEERING CAPSTONE PROJE...
MOVING FROM WATERFALL TO AGILE PROCESS IN SOFTWARE ENGINEERING CAPSTONE PROJE...MOVING FROM WATERFALL TO AGILE PROCESS IN SOFTWARE ENGINEERING CAPSTONE PROJE...
MOVING FROM WATERFALL TO AGILE PROCESS IN SOFTWARE ENGINEERING CAPSTONE PROJE...
 
PROMOTING STUDENT ENGAGEMENT USING SOCIAL MEDIA TECHNOLOGIES
PROMOTING STUDENT ENGAGEMENT USING SOCIAL MEDIA TECHNOLOGIESPROMOTING STUDENT ENGAGEMENT USING SOCIAL MEDIA TECHNOLOGIES
PROMOTING STUDENT ENGAGEMENT USING SOCIAL MEDIA TECHNOLOGIES
 
A SURVEY ON QUESTION ANSWERING SYSTEMS: THE ADVANCES OF FUZZY LOGIC
A SURVEY ON QUESTION ANSWERING SYSTEMS: THE ADVANCES OF FUZZY LOGICA SURVEY ON QUESTION ANSWERING SYSTEMS: THE ADVANCES OF FUZZY LOGIC
A SURVEY ON QUESTION ANSWERING SYSTEMS: THE ADVANCES OF FUZZY LOGIC
 
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
DYNAMIC PHONE WARPING – A METHOD TO MEASURE THE DISTANCE BETWEEN PRONUNCIATIONS
 
INTELLIGENT ELECTRONIC ASSESSMENT FOR SUBJECTIVE EXAMS
INTELLIGENT ELECTRONIC ASSESSMENT FOR SUBJECTIVE EXAMS INTELLIGENT ELECTRONIC ASSESSMENT FOR SUBJECTIVE EXAMS
INTELLIGENT ELECTRONIC ASSESSMENT FOR SUBJECTIVE EXAMS
 
TWO DISCRETE BINARY VERSIONS OF AFRICAN BUFFALO OPTIMIZATION METAHEURISTIC
TWO DISCRETE BINARY VERSIONS OF AFRICAN BUFFALO OPTIMIZATION METAHEURISTICTWO DISCRETE BINARY VERSIONS OF AFRICAN BUFFALO OPTIMIZATION METAHEURISTIC
TWO DISCRETE BINARY VERSIONS OF AFRICAN BUFFALO OPTIMIZATION METAHEURISTIC
 
DETECTION OF ALGORITHMICALLY GENERATED MALICIOUS DOMAIN
DETECTION OF ALGORITHMICALLY GENERATED MALICIOUS DOMAINDETECTION OF ALGORITHMICALLY GENERATED MALICIOUS DOMAIN
DETECTION OF ALGORITHMICALLY GENERATED MALICIOUS DOMAIN
 
GLOBAL MUSIC ASSET ASSURANCE DIGITAL CURRENCY: A DRM SOLUTION FOR STREAMING C...
GLOBAL MUSIC ASSET ASSURANCE DIGITAL CURRENCY: A DRM SOLUTION FOR STREAMING C...GLOBAL MUSIC ASSET ASSURANCE DIGITAL CURRENCY: A DRM SOLUTION FOR STREAMING C...
GLOBAL MUSIC ASSET ASSURANCE DIGITAL CURRENCY: A DRM SOLUTION FOR STREAMING C...
 
IMPORTANCE OF VERB SUFFIX MAPPING IN DISCOURSE TRANSLATION SYSTEM
IMPORTANCE OF VERB SUFFIX MAPPING IN DISCOURSE TRANSLATION SYSTEMIMPORTANCE OF VERB SUFFIX MAPPING IN DISCOURSE TRANSLATION SYSTEM
IMPORTANCE OF VERB SUFFIX MAPPING IN DISCOURSE TRANSLATION SYSTEM
 
EXACT SOLUTIONS OF A FAMILY OF HIGHER-DIMENSIONAL SPACE-TIME FRACTIONAL KDV-T...
EXACT SOLUTIONS OF A FAMILY OF HIGHER-DIMENSIONAL SPACE-TIME FRACTIONAL KDV-T...EXACT SOLUTIONS OF A FAMILY OF HIGHER-DIMENSIONAL SPACE-TIME FRACTIONAL KDV-T...
EXACT SOLUTIONS OF A FAMILY OF HIGHER-DIMENSIONAL SPACE-TIME FRACTIONAL KDV-T...
 
AUTOMATED PENETRATION TESTING: AN OVERVIEW
AUTOMATED PENETRATION TESTING: AN OVERVIEWAUTOMATED PENETRATION TESTING: AN OVERVIEW
AUTOMATED PENETRATION TESTING: AN OVERVIEW
 
CLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORK
CLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORKCLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORK
CLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORK
 
VALIDATION METHOD OF FUZZY ASSOCIATION RULES BASED ON FUZZY FORMAL CONCEPT AN...
VALIDATION METHOD OF FUZZY ASSOCIATION RULES BASED ON FUZZY FORMAL CONCEPT AN...VALIDATION METHOD OF FUZZY ASSOCIATION RULES BASED ON FUZZY FORMAL CONCEPT AN...
VALIDATION METHOD OF FUZZY ASSOCIATION RULES BASED ON FUZZY FORMAL CONCEPT AN...
 
PROBABILITY BASED CLUSTER EXPANSION OVERSAMPLING TECHNIQUE FOR IMBALANCED DATA
PROBABILITY BASED CLUSTER EXPANSION OVERSAMPLING TECHNIQUE FOR IMBALANCED DATAPROBABILITY BASED CLUSTER EXPANSION OVERSAMPLING TECHNIQUE FOR IMBALANCED DATA
PROBABILITY BASED CLUSTER EXPANSION OVERSAMPLING TECHNIQUE FOR IMBALANCED DATA
 
CHARACTER AND IMAGE RECOGNITION FOR DATA CATALOGING IN ECOLOGICAL RESEARCH
CHARACTER AND IMAGE RECOGNITION FOR DATA CATALOGING IN ECOLOGICAL RESEARCHCHARACTER AND IMAGE RECOGNITION FOR DATA CATALOGING IN ECOLOGICAL RESEARCH
CHARACTER AND IMAGE RECOGNITION FOR DATA CATALOGING IN ECOLOGICAL RESEARCH
 
SOCIAL MEDIA ANALYTICS FOR SENTIMENT ANALYSIS AND EVENT DETECTION IN SMART CI...
SOCIAL MEDIA ANALYTICS FOR SENTIMENT ANALYSIS AND EVENT DETECTION IN SMART CI...SOCIAL MEDIA ANALYTICS FOR SENTIMENT ANALYSIS AND EVENT DETECTION IN SMART CI...
SOCIAL MEDIA ANALYTICS FOR SENTIMENT ANALYSIS AND EVENT DETECTION IN SMART CI...
 
SOCIAL NETWORK HATE SPEECH DETECTION FOR AMHARIC LANGUAGE
SOCIAL NETWORK HATE SPEECH DETECTION FOR AMHARIC LANGUAGESOCIAL NETWORK HATE SPEECH DETECTION FOR AMHARIC LANGUAGE
SOCIAL NETWORK HATE SPEECH DETECTION FOR AMHARIC LANGUAGE
 
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXTGENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
 

Último

Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatYousafMalik24
 
FILIPINO PSYCHology sikolohiyang pilipino
FILIPINO PSYCHology sikolohiyang pilipinoFILIPINO PSYCHology sikolohiyang pilipino
FILIPINO PSYCHology sikolohiyang pilipinojohnmickonozaleda
 
Culture Uniformity or Diversity IN SOCIOLOGY.pptx
Culture Uniformity or Diversity IN SOCIOLOGY.pptxCulture Uniformity or Diversity IN SOCIOLOGY.pptx
Culture Uniformity or Diversity IN SOCIOLOGY.pptxPoojaSen20
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Celine George
 
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYKayeClaireEstoconing
 
4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptxmary850239
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPCeline George
 
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxBarangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxCarlos105
 
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)lakshayb543
 
ACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfSpandanaRallapalli
 
Science 7 Quarter 4 Module 2: Natural Resources.pptx
Science 7 Quarter 4 Module 2: Natural Resources.pptxScience 7 Quarter 4 Module 2: Natural Resources.pptx
Science 7 Quarter 4 Module 2: Natural Resources.pptxMaryGraceBautista27
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management SystemChristalin Nelson
 
Procuring digital preservation CAN be quick and painless with our new dynamic...
Procuring digital preservation CAN be quick and painless with our new dynamic...Procuring digital preservation CAN be quick and painless with our new dynamic...
Procuring digital preservation CAN be quick and painless with our new dynamic...Jisc
 
Judging the Relevance and worth of ideas part 2.pptx
Judging the Relevance  and worth of ideas part 2.pptxJudging the Relevance  and worth of ideas part 2.pptx
Judging the Relevance and worth of ideas part 2.pptxSherlyMaeNeri
 
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfLike-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfMr Bounab Samir
 
How to do quick user assign in kanban in Odoo 17 ERP
How to do quick user assign in kanban in Odoo 17 ERPHow to do quick user assign in kanban in Odoo 17 ERP
How to do quick user assign in kanban in Odoo 17 ERPCeline George
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parentsnavabharathschool99
 
4.16.24 21st Century Movements for Black Lives.pptx
4.16.24 21st Century Movements for Black Lives.pptx4.16.24 21st Century Movements for Black Lives.pptx
4.16.24 21st Century Movements for Black Lives.pptxmary850239
 

Último (20)

Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice great
 
FILIPINO PSYCHology sikolohiyang pilipino
FILIPINO PSYCHology sikolohiyang pilipinoFILIPINO PSYCHology sikolohiyang pilipino
FILIPINO PSYCHology sikolohiyang pilipino
 
Culture Uniformity or Diversity IN SOCIOLOGY.pptx
Culture Uniformity or Diversity IN SOCIOLOGY.pptxCulture Uniformity or Diversity IN SOCIOLOGY.pptx
Culture Uniformity or Diversity IN SOCIOLOGY.pptx
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17
 
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
 
4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx4.18.24 Movement Legacies, Reflection, and Review.pptx
4.18.24 Movement Legacies, Reflection, and Review.pptx
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERP
 
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxBarangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
 
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
Visit to a blind student's school🧑‍🦯🧑‍🦯(community medicine)
 
ACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdf
 
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptxYOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
 
Science 7 Quarter 4 Module 2: Natural Resources.pptx
Science 7 Quarter 4 Module 2: Natural Resources.pptxScience 7 Quarter 4 Module 2: Natural Resources.pptx
Science 7 Quarter 4 Module 2: Natural Resources.pptx
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management System
 
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptxYOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
 
Procuring digital preservation CAN be quick and painless with our new dynamic...
Procuring digital preservation CAN be quick and painless with our new dynamic...Procuring digital preservation CAN be quick and painless with our new dynamic...
Procuring digital preservation CAN be quick and painless with our new dynamic...
 
Judging the Relevance and worth of ideas part 2.pptx
Judging the Relevance  and worth of ideas part 2.pptxJudging the Relevance  and worth of ideas part 2.pptx
Judging the Relevance and worth of ideas part 2.pptx
 
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfLike-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
 
How to do quick user assign in kanban in Odoo 17 ERP
How to do quick user assign in kanban in Odoo 17 ERPHow to do quick user assign in kanban in Odoo 17 ERP
How to do quick user assign in kanban in Odoo 17 ERP
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parents
 
4.16.24 21st Century Movements for Black Lives.pptx
4.16.24 21st Century Movements for Black Lives.pptx4.16.24 21st Century Movements for Black Lives.pptx
4.16.24 21st Century Movements for Black Lives.pptx
 

Contextual Model Recommends Academic Resources

  • 1. Jan Zizka (Eds) : CCSIT, SIPP, AISC, PDCTA - 2013 pp. 421–429, 2013. © CS & IT-CSCP 2013 DOI : 10.5121/csit.2013.3648 CONTEXTUAL MODEL OF RECOMMENDING RESOURCES ON AN ACADEMIC NETWORKING PORTAL Anoop Kumar Pandey, Amit Kumar and Balaji Rajendran Centre for Development of Advanced Computing, Electronics City, Bangalore {anoop, amit, balaji}@cdac.in ABSTRACT Artificial Intelligence techniques have been instrumental in helping users to handle the large amount of information on the Internet. The idea of recommendation systems, custom search engines, and intelligent software has been widely accepted among users who seek assistance in searching, sorting, classifying, filtering and sharing this vast quantity of information. In this paper, we present a contextual model of recommendation engine which keeping in mind the context and activities of a user, recommends resources in an academic networking portal. The proposed method uses the implicit method of feedback and the concepts relationship hierarchy to determine the similarity between a user and the resources in the portal. The proposed algorithm has been tested on an academic networking portal and the results are convincing. KEYWORDS Contextual Model, Recommendation Engine, Academic Networking 1. INTRODUCTION The development of World Wide Web has contributed to a ever growing global society of internet users across the world. With exponential increase in users and thereby formation of avalanche of information, It has been quite difficult to segregate the information we actually need from amongst the mountain of web information. With need of a system for searching, sorting, filtering and sharing relevant information out of the information overload, several personalized search engines, recommender systems and intelligent software have been developed. A combination of modeling the preferences of particular users, building content models, and modeling social patterns in intelligent agents (Maes 1994) would provide users with a means for managing information in a rational way, thus helping them to overcome the overwhelming information content. Recommender Systems or Recommendation Systems are quite common and used in several applications. They primarily identify interesting information for a given user such as their likely taste for a type of music, book, or movie or the most likely kind of people or groups whom they would want to be associated with. , The common approaches adopted by these systems are: Content-based filtering that use characteristics of an item or Collaborative filtering that rely on a use’s profile and their social network [4]. Some examples are:
  • 2. 422 Computer Science & Information Technology (CS & IT) • When viewing a product on Amazon, the store will recommend additional items based on a matrix of what other shoppers bought along with the currently selected item.[8] • Friends suggestion on Facebook.[6] • People, group, job suggestion on LinkedIn.[7] • Follow suggestions on Twitter.[9] Figure 1. Examples of various recommendations from social media In a relatively short time, several recommender agents have been developed and there is a wide variety of such systems, all of which exploit a particular set of AI techniques. Recommender systems typically produce a list of recommendations in one of the three main information filtering methods: demographic, content based and collaborative [1]. Demo graphic filtering approaches us e descriptions of people to learn the relationship between a single item and the type of people who like it. Content -based filtering approaches recommend items for the user based on the descriptions of previously evaluated items. The collaborative filtering technique matches people with similar interests and then makes recommendations on this basis. Another approach to overcome the shortcomings of collaborative and content based filtering is Hybrid systems that exploit features of content-based and collaborative filtering, since they will almost certainly prove to be complementary. Each type of system has its own strengths and weaknesses. The proposed algorithm of recommender system exploits user profile, implicit feedback and explicitly cited interests. The algorithm uses a concept hierarchy, that holds all the concepts used in the domain, which will be used to determine the context of the user and the resources to be recommended, having similarity with user's interest. The rest of this paper is organized as follows. Section 2 discusses some of the recommendation techniques used in recommender agents in general and in academic environments. Section 3 details the proposed recommendation system for academic portals. Section 4 discusses the impact of our proposed algorithm and results and section 5 concludes the paper.
  • 3. Computer Science & Information Technology (CS & IT) 423 2. RELATED WORKS In this section we briefly present some of the research literature review related to recommender systems in general, academic recommendation system, and evaluation of recommender systems. Recommender systems typically produce a list of recommendations using one of the four main information filtering methods [10]: demographic filtering, collaborative filtering, content-based filtering, and hybrid methods. First, demographic filtering approaches use descriptions of people to learn the relationship between a single item and the type of people who like it. Collaborative filtering uses user-item rating matrix for predicting unseen preferences [11, 12]. It can be categorized into memory -based CF, which contains the whole matrix on memory, and model-based CF, that involves building a model for estimation [13]. The most effective memory-based algorithms known so far is item-based CF [19]. Matrix factorization, a kind of model-based approach, known to be most efficient and accurate, especially after this approach won the Netflix prize in 2009, is being used in many recent works [14, 16, 18, 17, 20]. Content- based filtering, on the other hand, recommends items based on their characteristics as well as based on previous evaluations of a user [10]. Pazzani et al. [15] studied this approach in depth, including how to build user and item profiles. Hybrid approach, tries to combine both collaborative and content-based recommendation. Koren [21] suggested effectively combining rating information and user, item profiles for more accurate recommendation. In [2], we used the contextual method of detecting relevant content for a user using a concept hierarchy and concept extraction method. In [22] the authors had defined similarity between two research papers based on the text similarity between them and then proposed their recommender system developed using collaborative filtering methods. AACORN [23], a course recommendation system that uses the course histories as the basis for course advising. By reusing the experience embodied in historical student's transcripts, AACORN can make reasonable suggestions with a limited amount of domain knowledge. The system uses the edit distance between two course histories, as well as other heuristics to determine the similarity between course histories. 3. CONTEXTUAL METHOD OF RECOMMENDATION The Contextual Model of Recommendation System is built into a system that recommends different resources viz. institutions, courses, events, projects, topic, and persons to ‘Follow’ and get updates, to the various users of our academic networking portal. The users could be. students, faculties, researchers, representatives of institutions etc, whose sole aim is to discover and share information about their subjects of interest, information about institutions, courses, events, projects, questionnaires, and such related activities for learning and research. In this pursuit, they would like to receive regular updates regarding their favourite courses, persons, topics and important notifications regarding events like seminars, conference and workshop etc. For this purpose they “Follow” particular resource in which they are interested in. While there are thousands of resources on the academic portal, it is a tedious job to search out resources of own interest and check the latest updates. The criticality of recommendation system will guide the user to sift through such large information by recommending them the appropriate resources based on their profile, their explicit and implicit feedback. We start by defining the common terms that are used in our system, following it with the recommendation algorithm.
  • 4. 424 Computer Science & Information Technology (CS & IT) 3.1. Definitions Resource: All components of our academic networking website are treated as resources. Examples may include institutes, faculties, courses, events, projects, web links, topics etc. Our recommendation system recommends these resources to the user to ‘Follow’. Concepts & Relationships: Concept in general, could refer to all the terminologies and vocabulary of a particular domain which is used to describe it. The definition of concepts and relationship between the concepts is typically captured in the form of ontology for a domain. We use a simple structure called concept tree that captures two kinds of relationships: is-a and is-in. For instance in the statement, “Java is an Object-oriented language”, the concepts ‘Java’ and ’object-oriented language’ are captured using ‘is-a’ relationship. The is-in relationship is captured as a composition tree. For instance, “Object-oriented Languages” is contained within the concept of “Programming Languages”. N.B.: All resources are concepts. Concept Extraction: It is the process of extracting the concepts in a given piece of text, by comparing the main terms with the concept tree. Co-occurrence Pattern: It defines the pattern and frequency of a concept occurring with another concept within a defined window. E.g. Sachin and Cricket co-occurs with each other often. Follow List: Resources, a user is already watching. Posts: Informative content posted on a resource’s wall/timeline. Cosine Similarity: Cosine similarity is a measure of similarity between two vectors by measuring the cosine of the angle between them. The cosine of the angle between two vectors thus determines whether two vectors are pointing in roughly the same direction. 3.2. Steps towards Algorithm In the proposed recommendation algorithm, we use three parameters – User’s Profile, User’s Follow List, and User’s Navigation History as input to our algorithm for determining the likely list of resources that a user would be interested in. A factor of weight has been given to each of these parameters so that the results are not skewed to a single parameter. They are assigned as high for explicit and low for implicit parameters. The user profile will explicitly contain the user’s skill-set, experience and areas of interest. The user’s follow list indicates the resources that the user is interested in getting the recent updates of that particular resource. The user’s navigation history is an implicit parameter that reveals the interests of the user. When we have a set of resources, the user is interested in, concepts are extracted from them through contextual method and then we try to find out if some other resource also belong to or matches with the same pool of resources. If we find resources in that pool which the user is currently unaware of, then they are recommended to the user. The recommendations are generated dynamically – i.e., on the live and changing data.
  • 5. Computer Science & Information Technology (CS & IT) 425 3.3. Algorithm for recommendation generation Assumptions: a) Presence of concept extraction algorithm. b) Presence of concept and containment trees. c) Resource R has been properly modeled. d) Presence of Co-occurrence table based on descriptions of concepts. Input: User’s Profile, User’s Follow List, User’s Navigation Pattern. Output: Set of recommendation comprising 3 resources. Algorithm: Extract the concepts from User Profile Columns: “Skill-Set”, “Experience”, “Area of Interest”. Store it in an associative array CUP with key as concept-id and value as term frequency of occurrence. Extract the concepts from user’s Follow list and store it in an array CFL with corresponding term frequency. Extract the concepts from user’s navigation list and store it in an array CNL with corresponding term frequency. Combine the array in one array with different weightages. C = 3*CUP + 2*CFL + 0.25*CNL Expand the concept-list C based on co-occurrence table and update the frequency as well. CEX = C U (Concepts co-occurring with C). Create Weight vector of length ‘n’, where n is the total no of concepts in CEX. = [wi] where wi is the weightage or term frequency of concepts within CEX Represent each resource as a vector , which the user is not watching, in terms of the concepts in CEX and their corresponding term frequency in the resource description and the posts on the resource’s wall in last one year. For each resource calculate cosine similarity (Cosim) with concept vector representing the user interest as: Cosim ( ) = . / Arrange the resources in decreasing order of cosine similarity value. Filter out top ‘u’ resources as per following rule: = 0.8 * Find out top u resources and recommend any 3 out of them. 4. IMPLEMENTATION AND RESULTS An academic networking portal [27], with interactive features for its users was used for validating our approach. The website features the recommendation system with facility to hover over recommendation to watch information, click to navigate to the resource page and Follow button to accept recommendation. Figure 2 and 3 illustrate the recommendation and hover function. We captured each action (hover, click and Follow) corresponding to a particular recommended resource while user was presented with three recommendations on a page. These actions were treated as metrics for evaluation in addition to manual inspection, where the recommended resources were checked to whether having the similarity with user's interest and trend.
  • 6. 426 Computer Science & Information Technology (CS & IT) Figure 2. Screenshot of recommendation of resources (institutions and person) Figure 3. Examples of various recommendations with hover effect. In manual inspection, the results were pretty impressive with recommended resources amounting to 85-90% similarity with user's interest. The test was conducted with 70 user's profile matching with recommended resources. The recommendation system was also tested from user's perspective and in terms of effectiveness/usefulness of the recommendation. Corresponding to a user, for each set of recommendations, user's actions viz. 'Click', 'Hover', and 'Watch' were captured. The data collected was analysed to check how recommended resources had been considered useful. Table 1 describes the total recommendations received by each user and the summary of actions taken by the users:
  • 7. Computer Science & Information Technology (CS & IT) 427 Table 1 Statistics of various actions to check effectiveness of the proposed solution. User/Action Total Recommendations Hover Click Watch U1 15 14(93.3%) 12(80%) 9(60%) U2 24 21(87.5%) 19(79.2%) 17(70.8%) U3 18 16(88.9%) 13(72.2%) 11(61.1%) U4 12 12(100%) 11(91.7%) 9(75%) U5 33 31(93.9%) 28(84.8%) 24(72.7%) U6 9 9(100%) 9(100%) 6(66.7%) - - Total 966 907(93.9%) 788(81.6%) 693(71.7%) The results were quite impressive as majority of the presented recommendations 94% were hovered for information display, 82% were clicked to view full information and 72% were accepted for following. Considering the action taken by the user in terms of their „Following‟ a resource, the results are quite impressive. 5. CONCLUSIONS In this paper, we have presented a Contextual Model of Resource Recommendation System for academic portals, which recommends different resources viz. Institution, course, project, topic, event and academician to the users of the portal. The proposed system determines the concepts and cosine similarity between them with understanding of context and identifies potential resources to be recommended to the user based on user's profile and their explicit as well as implicit feedbacks. Evaluation results show the utility of our proposed system. We made the assumption that the resources in the system have been well defined and modeled. We also assumed the existence of ontology in terms of concept tree with simple relationships that defines the domain in which the academic portal operates. This methodology could be easily extended to other domain-specific vertical portals, though the challenge would be in extending it to a generic and interactive information system. REFERENCES [1] Miquel Montaner, Beatriz Lopez and Josep Lluis De La Rosa: A Taxonomy of Recommender Agents on the Internet Artificial Intelligence Review 19: 285–330, 2003. [2] Balaji Rajendran and Anoop Kumar Pandey, “Contextual Strategies for Detecting Spam in Academic Portals”, The 2nd International Conference on Computer Science and Information Technology (CCSIT-2012), Royal Orchid Central, Bangalore, January 2-4, 2012. [3] Jennings, A. & Higuchi, H. (1993). A User Model Neural Network for a Personal News Service. User Modeling and User-Adapted Interaction 3: 1–25. [4] Recommender Systems, http://en.wikipedia.org/wiki/Recommender_system [5] Morita, M. & Shinoda, Y. (1994). Information Filtering Based on User Behaviour Analysis and Best Match Text Retrieval. In Proceedings of SIGIR‟94, 272–81. Dublin, Ireland: Springer-Verlag. [6] Facebook, http://www.facebook.com [7] LinkedIn, http://www.linkedin.com [8] Amazon, http://www.amazon.com [9] Twitter, http://www.twitter.com
  • 8. 428 Computer Science & Information Technology (CS & IT) [10] D. Jannach, M. Zanker, A. Felfernig, and G. Friedrich. Recommender Systems. An Introduction. Cambridge, 2011. [11] X. Su and T. M. Khoshgoftaar. A survey of collaborative filtering techniques. Adv. in Artif. Intell, 2009:4:2.4:2, January 2009. [12] G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Enginerring, 17(6):734.749, 2005. [13] J. S. Breese, D. Heckerman, and C. Kadie. Empirical analysis of predictive algorithms for collaborative filtering. pages 43.52. Morgan Kaufmann, 1998. [14] A. Paterek. Improving regularized singular value decomposition for collaborative filtering. Statistics, 2007:2.5. [15] M. Pazzani and D. Billsus. Content-based recommendation systems. In P. Brusilovsky, A. Kobsa, and W. Nejdl, editors, The Adaptive Web, volume 4321 of Lecture Notes in Computer Science, pages 325.341. Springer Berlin, Heidelberg, 2007. [16] J. D. M. Rennie and N. Srebro. Fast maximum margin matrix factorization for collaborative prediction. In Proceedings of the 22nd international conference on Machine learning, ICML .05, pages 713.719, New York, NY, USA, 2005. ACM. [17] L. D. D. Algorithms for nonnegative matrix factorization. Advances in Neural Information Processing Systems, 13:556.562, 2001. [18] R. Salakhutdinov and A. Mnih. Probabilistic matrix factorization. 2008. [19] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Item-based collaborative filtering recommendation algorithms. Pages 285.295, 2001. [20] K. Yu, S. Zhu, J. Lafferty, and Y. Gong. Fast nonparametric matrix factorization for large-scale collaborative filtering. In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, SIGIR .09, pages 211.218, New York, NY, USA, 2009. ACM. [21] Y. Koren. Factorization meets the neighborhood: a multifaceted collaborative filtering model. In Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD ‟08, pages 426–434, New York, NY, USA, 2008. ACM. [22] Joonseok Lee, Kisung Lee, Jennifer G. Kim: Personalized Academic Research Paper Recommendation System, http://www.cc.gatech.edu/~jkim693/ projects / recommendation.pdf, Georgia Institute of Technology, Atlanta, GA. [23] JJ Sandvig, Robin Burke: AACORN: A CBR Recommender for Academic Advising, http://facweb.cti.depaul.edu/research/techreports/TR05-015.doc [24] K. Sugiyama and M.-Y. Kan. Scholarly paper recommendation via user‟s recent research interests. In Proceedings of the 10th annual joint conference on Digital libraries, JCDL ‟10, pages 29–38, New York, NY, USA, 2010. ACM. [25] Tang and J. Zhang. A discriminative approach to topic-based citation recommendation. In T. Theeramunkong, B. Kijsirikul, N. Cercone, and T.-B. Ho, editors, Advances in Knowledge Discovery and Data Mining, volume 5476 of Lecture Notes in Computer Science, pages 572–579. Springer Berlin / Heidelberg, 2009. [26] K. Yu, S. Zhu, J. Lafferty, and Y. Gong. Fast nonparametric matrix factorization for large-scale collaborative filtering. In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, SIGIR ‟09, pages 211–218, New York, NY, USA, 2009. ACM. [27] Seekha, http://www.seekha.in
  • 9. Computer Science & Information Technology (CS & IT) 429 Authors Anoop Kumar Pandey Mr Anoop Kumar Pandey holds a B. Tech degree in CSE graduate (2010) from Shri Mata Vaishno Devi University, Jammu. He was a Chancellor Gold Medalist. He joined C-DAC after the college and currently working here as a Technical Officer. He is also pursuing MS by Research from IIIT Bangalore, India. Amit Kumar Mr Amit Kumar completed his B.Tech in CSE, from Biju Patnaik University of Technology (BPUT), Orissa. He currently works as a Project Engineer at CDAC since 2011. His current work of area is web application developmentt and Disaster Recovery site management and maintenance. His interest area includes web-design, database management system, and information security. Dr Balaji Rajendran Dr Balaji Rajendran holds a Ph.D degree from Madurai Kamaraj University and is currently working as a Senior Technical officer at CDAC Bangalore. He has 11+ years of experience in teaching and R&D. His interest area and domain expertise include information security, web information systems, social media and intelligence.