SlideShare a Scribd company logo
1 of 29
Download to read offline
A multidimensional expertise recommender tool
Germ´an S´anchez-Hern´andez, Jennifer Nguyen, N´uria Agell, Cecilio Angulo
June 24th, 2015
Introduction
State of the art
Arquitecture
User interface
Conclusions
Outline
1 Introduction
2 State of the art
3 Arquitecture
4 User interface
5 Conclusions
2 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Motivation and framework
Outline
1 Introduction
2 State of the art
3 Arquitecture
4 User interface
5 Conclusions
3 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Motivation and framework
Motivation and framework
www.projectcollage.eu
Creative learning is social, collaborative and peer based.
Expand and foster interaction among users with different
backgrounds, opinions and levels of expertise
→ improvement of creativity.
Find people with expertise in some areas
(“right level of expertise” vs. “right person”)
4 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Related work
Outline
1 Introduction
2 State of the art
3 Arquitecture
4 User interface
5 Conclusions
5 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Related work
Related work of ERS
MITRE’s Expert Finder [Mattox et al., 1999]: experts in
topics. Associations author-term in internal documents.
Search by keywords.
NASA POPS [Grove and Schain, 2008]: filtering experts by
organisation, project or competency. Use of RDF, multiple
databases, semantic web.
IBM SmaillBlue [Lin et al., 2008; 2009]: expertise in emails and
chat, mapping search strings to keywords.
INDURE FacFinder [Fang et al., 2008]: information from
faculty profiles and homepages, all internal documents
indexed. Proximity of terms. Considers order, source and rank
of source.
StrangersRS [Guy et al., 2011]: recommendation of people with
similar interests but unfamiliar.
6 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Related work
Lacks
Just expertise
Information treatment:
Filtering candidates
Parameters required (weights, thresholds)
→ Premature discards
7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Related work
Lacks
Just expertise
Information treatment:
Filtering candidates
Parameters required (weights, thresholds)
→ Premature discards
7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Related work
Lacks
Just expertise
Information treatment:
Filtering candidates
Parameters required (weights, thresholds)
→ Premature discards
7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Related work
Lacks
Just expertise
Information treatment:
Filtering candidates
Parameters required (weights, thresholds)
→ Premature discards
7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Related work
Lacks
Just expertise
Information treatment:
Filtering candidates
Parameters required (weights, thresholds)
→ Premature discards
7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Outline
1 Introduction
2 State of the art
3 Arquitecture
4 User interface
5 Conclusions
8 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Arquitecture
9 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Arquitecture
Profiling
Profiling module
Candidates’ profiles
Access to Collage User
Profile Service
Offline massive update
Online selective update
10 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Profiles
Skill Profiling CER
Expertise Areas of knowledge
Four qualitative levels
(none, high, medium, low)
Qualities/Subskills Other knowledge Specific tools
Proximity Ease to contact
Physical distance
High or low
Availability Current availability
Manual update
Four levels
11 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Arquitecture
Interaction
Interaction module
Interaction with the user
Translates preferences to
requirements
Explicit
Implicit (user profile)
Controls for selecting final
experts
12 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Arquitecture
Identification
Identification module
Initial list of candidates
Access to profiles
Feasible candidates
13 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Arquitecture
Selection
Selection module
Assessing each candidate
Aggregating assessments
Ranking and selection of
candidates
14 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Selection of candidates
Assessment
One assessment per requirement. Fuzzy distance between the
requirement and the fulfillment.
Expertise: Ae(ps, l) = min(ps ,l)
l .
Subskill: Aq(ps) = ps.
Proximity: distance between user and candidate.
Ap(pd ) =
1 − pd −md
Md −md
if high proximity is required,
pd −md
Md −md
otherwise.
Availability: distance to (high) required availability
Aa(pa) = pa. (1)
(ps , pd and pa are related to the profile of the candidate; l is the required
level of expertise; md and Md are the minimum and maximum distances
between departments.)
15 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Arquitecture
CER
Selection of candidates
Aggregation and Ranking
Operator: OWA.
Weights: linguistic quantifier
wi = Q
i
n
− Q
i − 1
n
, i = 1, . . . , n.
“most of”: Q(r) = r
1
2 .
16 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Outline
1 Introduction
2 State of the art
3 Arquitecture
4 User interface
5 Conclusions
17 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Current UI
Input form
18 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
New UI
Input form
19 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Current UI
Results
20 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
New UI
Results
21 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Outline
1 Introduction
2 State of the art
3 Arquitecture
4 User interface
5 Conclusions
22 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Conclusions and Next Steps
Expertise recommender to find the right expert.
Right level of expertise vs. right person.
Additional information used: qualities, proximity, availability.
Integration into an existing platform (end users’ affinity space,
Moodle).
Information available in end users’ systems.
Improving prototype.
Team forming.
23 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Introduction
State of the art
Arquitecture
User interface
Conclusions
Conclusions and Next Steps
Expertise recommender to find the right expert.
Right level of expertise vs. right person.
Additional information used: qualities, proximity, availability.
Integration into an existing platform (end users’ affinity space,
Moodle).
Information available in end users’ systems.
Improving prototype.
Team forming.
23 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
Thank you!
Germ´an S´anchez-Hern´andez
german.sanchez@esade.edu

More Related Content

Viewers also liked

European week, Karmelava kindergarten, KA2
European week, Karmelava kindergarten, KA2European week, Karmelava kindergarten, KA2
European week, Karmelava kindergarten, KA2Jolanta Varanaviciene
 
Days of traditional tales in the Netherlands KA2
Days of traditional tales in the Netherlands KA2Days of traditional tales in the Netherlands KA2
Days of traditional tales in the Netherlands KA2Jolanta Varanaviciene
 
Apresentação dissertação Mestrado
Apresentação dissertação MestradoApresentação dissertação Mestrado
Apresentação dissertação MestradoMónica Correia
 
匯流五法:整體說明
匯流五法:整體說明匯流五法:整體說明
匯流五法:整體說明vTaiwan.tw
 
Social Media Marketing Overview Share
Social Media Marketing Overview ShareSocial Media Marketing Overview Share
Social Media Marketing Overview ShareSROshinski
 
"Saulės" privati gimnazija. Elektroninė mokinio byla
"Saulės" privati gimnazija. Elektroninė mokinio byla"Saulės" privati gimnazija. Elektroninė mokinio byla
"Saulės" privati gimnazija. Elektroninė mokinio bylaKnowledge Economy Forum
 
Cosas que me gustan y no me gustan
Cosas que me gustan y no me gustanCosas que me gustan y no me gustan
Cosas que me gustan y no me gustanfengchuishaster
 
Cloud-based Education: Scenarios for the Future
Cloud-based Education: Scenarios for the FutureCloud-based Education: Scenarios for the Future
Cloud-based Education: Scenarios for the FutureTheSoFGr
 
失控的有線電視結構
失控的有線電視結構失控的有線電視結構
失控的有線電視結構Yun-Ting Chen
 
International Womens Day photos from Reuters
International Womens Day photos from ReutersInternational Womens Day photos from Reuters
International Womens Day photos from ReutersJill Koppel
 
公司法公司董監事選任制度變革
公司法公司董監事選任制度變革公司法公司董監事選任制度變革
公司法公司董監事選任制度變革vTaiwan.tw
 
Ugdymo strategijų įtaka ugdymo kokybei
Ugdymo strategijų įtaka ugdymo kokybeiUgdymo strategijų įtaka ugdymo kokybei
Ugdymo strategijų įtaka ugdymo kokybeiJolanta Varanaviciene
 

Viewers also liked (13)

European week, Karmelava kindergarten, KA2
European week, Karmelava kindergarten, KA2European week, Karmelava kindergarten, KA2
European week, Karmelava kindergarten, KA2
 
Days of traditional tales in the Netherlands KA2
Days of traditional tales in the Netherlands KA2Days of traditional tales in the Netherlands KA2
Days of traditional tales in the Netherlands KA2
 
Diário Oficial: 04-12-2015
Diário Oficial: 04-12-2015 Diário Oficial: 04-12-2015
Diário Oficial: 04-12-2015
 
Apresentação dissertação Mestrado
Apresentação dissertação MestradoApresentação dissertação Mestrado
Apresentação dissertação Mestrado
 
匯流五法:整體說明
匯流五法:整體說明匯流五法:整體說明
匯流五法:整體說明
 
Social Media Marketing Overview Share
Social Media Marketing Overview ShareSocial Media Marketing Overview Share
Social Media Marketing Overview Share
 
"Saulės" privati gimnazija. Elektroninė mokinio byla
"Saulės" privati gimnazija. Elektroninė mokinio byla"Saulės" privati gimnazija. Elektroninė mokinio byla
"Saulės" privati gimnazija. Elektroninė mokinio byla
 
Cosas que me gustan y no me gustan
Cosas que me gustan y no me gustanCosas que me gustan y no me gustan
Cosas que me gustan y no me gustan
 
Cloud-based Education: Scenarios for the Future
Cloud-based Education: Scenarios for the FutureCloud-based Education: Scenarios for the Future
Cloud-based Education: Scenarios for the Future
 
失控的有線電視結構
失控的有線電視結構失控的有線電視結構
失控的有線電視結構
 
International Womens Day photos from Reuters
International Womens Day photos from ReutersInternational Womens Day photos from Reuters
International Womens Day photos from Reuters
 
公司法公司董監事選任制度變革
公司法公司董監事選任制度變革公司法公司董監事選任制度變革
公司法公司董監事選任制度變革
 
Ugdymo strategijų įtaka ugdymo kokybei
Ugdymo strategijų įtaka ugdymo kokybeiUgdymo strategijų įtaka ugdymo kokybei
Ugdymo strategijų įtaka ugdymo kokybei
 

Recently uploaded

{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
 
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girlCall Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girlkumarajju5765
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Delhi Call girls
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxolyaivanovalion
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFxolyaivanovalion
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxolyaivanovalion
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxMohammedJunaid861692
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxolyaivanovalion
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxfirstjob4
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusTimothy Spann
 
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...shivangimorya083
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...amitlee9823
 

Recently uploaded (20)

{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girlCall Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
Call Girls 🫤 Dwarka ➡️ 9711199171 ➡️ Delhi 🫦 Two shot with one girl
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
Best VIP Call Girls Noida Sector 22 Call Me: 8448380779
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Smarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptxSmarteg dropshipping via API with DroFx.pptx
Smarteg dropshipping via API with DroFx.pptx
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptx
 
Introduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptxIntroduction-to-Machine-Learning (1).pptx
Introduction-to-Machine-Learning (1).pptx
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...Vip Model  Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
Vip Model Call Girls (Delhi) Karol Bagh 9711199171✔️Body to body massage wit...
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 

A multidimensional expertise recommender tool

  • 1. A multidimensional expertise recommender tool Germ´an S´anchez-Hern´andez, Jennifer Nguyen, N´uria Agell, Cecilio Angulo June 24th, 2015
  • 2. Introduction State of the art Arquitecture User interface Conclusions Outline 1 Introduction 2 State of the art 3 Arquitecture 4 User interface 5 Conclusions 2 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 3. Introduction State of the art Arquitecture User interface Conclusions Motivation and framework Outline 1 Introduction 2 State of the art 3 Arquitecture 4 User interface 5 Conclusions 3 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 4. Introduction State of the art Arquitecture User interface Conclusions Motivation and framework Motivation and framework www.projectcollage.eu Creative learning is social, collaborative and peer based. Expand and foster interaction among users with different backgrounds, opinions and levels of expertise → improvement of creativity. Find people with expertise in some areas (“right level of expertise” vs. “right person”) 4 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 5. Introduction State of the art Arquitecture User interface Conclusions Related work Outline 1 Introduction 2 State of the art 3 Arquitecture 4 User interface 5 Conclusions 5 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 6. Introduction State of the art Arquitecture User interface Conclusions Related work Related work of ERS MITRE’s Expert Finder [Mattox et al., 1999]: experts in topics. Associations author-term in internal documents. Search by keywords. NASA POPS [Grove and Schain, 2008]: filtering experts by organisation, project or competency. Use of RDF, multiple databases, semantic web. IBM SmaillBlue [Lin et al., 2008; 2009]: expertise in emails and chat, mapping search strings to keywords. INDURE FacFinder [Fang et al., 2008]: information from faculty profiles and homepages, all internal documents indexed. Proximity of terms. Considers order, source and rank of source. StrangersRS [Guy et al., 2011]: recommendation of people with similar interests but unfamiliar. 6 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 7. Introduction State of the art Arquitecture User interface Conclusions Related work Lacks Just expertise Information treatment: Filtering candidates Parameters required (weights, thresholds) → Premature discards 7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 8. Introduction State of the art Arquitecture User interface Conclusions Related work Lacks Just expertise Information treatment: Filtering candidates Parameters required (weights, thresholds) → Premature discards 7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 9. Introduction State of the art Arquitecture User interface Conclusions Related work Lacks Just expertise Information treatment: Filtering candidates Parameters required (weights, thresholds) → Premature discards 7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 10. Introduction State of the art Arquitecture User interface Conclusions Related work Lacks Just expertise Information treatment: Filtering candidates Parameters required (weights, thresholds) → Premature discards 7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 11. Introduction State of the art Arquitecture User interface Conclusions Related work Lacks Just expertise Information treatment: Filtering candidates Parameters required (weights, thresholds) → Premature discards 7 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 12. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Outline 1 Introduction 2 State of the art 3 Arquitecture 4 User interface 5 Conclusions 8 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 13. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Arquitecture 9 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 14. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Arquitecture Profiling Profiling module Candidates’ profiles Access to Collage User Profile Service Offline massive update Online selective update 10 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 15. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Profiles Skill Profiling CER Expertise Areas of knowledge Four qualitative levels (none, high, medium, low) Qualities/Subskills Other knowledge Specific tools Proximity Ease to contact Physical distance High or low Availability Current availability Manual update Four levels 11 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 16. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Arquitecture Interaction Interaction module Interaction with the user Translates preferences to requirements Explicit Implicit (user profile) Controls for selecting final experts 12 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 17. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Arquitecture Identification Identification module Initial list of candidates Access to profiles Feasible candidates 13 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 18. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Arquitecture Selection Selection module Assessing each candidate Aggregating assessments Ranking and selection of candidates 14 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 19. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Selection of candidates Assessment One assessment per requirement. Fuzzy distance between the requirement and the fulfillment. Expertise: Ae(ps, l) = min(ps ,l) l . Subskill: Aq(ps) = ps. Proximity: distance between user and candidate. Ap(pd ) = 1 − pd −md Md −md if high proximity is required, pd −md Md −md otherwise. Availability: distance to (high) required availability Aa(pa) = pa. (1) (ps , pd and pa are related to the profile of the candidate; l is the required level of expertise; md and Md are the minimum and maximum distances between departments.) 15 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 20. Introduction State of the art Arquitecture User interface Conclusions Arquitecture CER Selection of candidates Aggregation and Ranking Operator: OWA. Weights: linguistic quantifier wi = Q i n − Q i − 1 n , i = 1, . . . , n. “most of”: Q(r) = r 1 2 . 16 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 21. Introduction State of the art Arquitecture User interface Conclusions Outline 1 Introduction 2 State of the art 3 Arquitecture 4 User interface 5 Conclusions 17 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 22. Introduction State of the art Arquitecture User interface Conclusions Current UI Input form 18 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 23. Introduction State of the art Arquitecture User interface Conclusions New UI Input form 19 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 24. Introduction State of the art Arquitecture User interface Conclusions Current UI Results 20 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 25. Introduction State of the art Arquitecture User interface Conclusions New UI Results 21 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 26. Introduction State of the art Arquitecture User interface Conclusions Outline 1 Introduction 2 State of the art 3 Arquitecture 4 User interface 5 Conclusions 22 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 27. Introduction State of the art Arquitecture User interface Conclusions Conclusions and Next Steps Expertise recommender to find the right expert. Right level of expertise vs. right person. Additional information used: qualities, proximity, availability. Integration into an existing platform (end users’ affinity space, Moodle). Information available in end users’ systems. Improving prototype. Team forming. 23 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender
  • 28. Introduction State of the art Arquitecture User interface Conclusions Conclusions and Next Steps Expertise recommender to find the right expert. Right level of expertise vs. right person. Additional information used: qualities, proximity, availability. Integration into an existing platform (end users’ affinity space, Moodle). Information available in end users’ systems. Improving prototype. Team forming. 23 / 24 Germ´an S´anchez-Hern´andez JARCA 2015: Expertise Recommender