SlideShare uma empresa Scribd logo
1 de 36
BULE HORA UNIVERSITY
COLLEGE OF INFORMATICS
COMPUTER SCIENCE DEPARTMENT
Aspect Based Sentiment Analysis
of Afaan Oromoo Movie Reviews Using
Machine Learning Techniques
By
Obsa Gelchu
Advisor: Kula kekeba (PhD)
Presentation Outline
Introduction
Statements of Problem
Research Questions
 Objective of the study
Scope and Limitation
Significance of the Study
Summary of Related work
Research Gap
Research Methodology
Experimental Results and Discussion
Conclusion, Contribution and Recommendation
3/27/2023 2
Introduction
Sentiment Analysis (SA)
SA is increasingly viewed as vital task both from
academic and commercial stand point.
Basically, SA is NLP techniques used to identify
and categorize attitude of reviewers to respective
topics as positive, negative, or neutral.
3/27/2023 3
Introduction…
Levels of Sentiment Analysis
3/27/2023
4
Sentiment
Analysis
Document
level
Sentence
level
Aspect
level
Introduction…
 Document level and Sentence level SA
Considered overall polarity of the reviewed text
regardless attributes of an entity.
 However, Comments of the reviewer may contain
different aspects/features.
Ex: “The story of the movie is good but the acting
of the actors is awful”.
Aspect terms: {message, acting}
Aspect Polarity: {message, #positive, acting,
#negative}
5
Introduction…
Aspect Based Sentiment Analysis (ABSA)
ABSA is sub-level of SA which extracts aspect of
each topic from reviewer sentence with its
corresponding sentiment polarity.
Ex: “The actor is so good, but this movie just horrible”.
Aspect terms: {actor, movie }
Aspect polarity: {actor, #positive , movie, #negative}
3/27/2023
6
Statement of the Problem
With the emergency of social media, comments to
particular entity in business industry are increasing
daily from the behalf of users/customers.
Opinions can influence the thinking of human
beings as humans always want to know the
opinions of others in every decision they may
made.
3/27/2023 7
Statement of the Problem…
To summarize thousands opinions of users to
respective topics, different scholars were
investigated SA only at document and sentence
level regardless of its features.
Comments of the users may contain different
aspects/features.
Ex: “The actor is so good, but this movie just
horrible”.
Aspect terms: {actor, movie}
3/27/2023 8
Statement of the Problem …
Analyzing opinion of reviewers only at document
and sentence level SA cannot provide sufficient
information.
To analyse the opinions of customers at fine-
grained level, ABSA was proposed to analyse
Afaan Oromoo movie reviews using machine
learning techniques.
3/27/2023 9
Research Questions
1. Which Machine learning model is most
appropriate for Afaan Oromoo ABSA for movie
reviews?
2. What are the best attributes for Afaan Oromoo
movie reviews for ABSA?
3. What are the main challenges in building Afaan
Oromoo ABSA dataset for movie reviews?
4. What is the performance of the proposed ABSA
system?
3/27/2023 10
Objectives
 General objective
To design and develop ABSA model for Afaan
Oromoo movie reviews using machine learning
techniques.
Specific Objectives
To review SA related work for ABSA of AO movie
reviews.
To investigate appropriate strategies to prepare
ABSA dataset for Afaan Oromoo movie reviews.
To explore how aspect-based opinions could be
designed and implemented for Afaan Oromoo
movie entertainment.
3/27/2023 11
Objectives…
Specific Objectives….
To develop different machine learning models for
Afaan Oromoo ABSA for movie reviews.
To evaluate the performance of the proposed
models for Afaan Oromoo movie reviews.
To prepare Afaan Oromoo ABSA dataset for
movie reviews.
Based on the gained result, to propose a set of
improvements and to suggest recommendations.
3/27/2023 12
Scope and Limitation of Study
The objective of the study is to design and
develop ABSA model for Afaan Oromoo movie
reviews using machine learning techniques.
For this purpose we have focused on:
 Afaan Oromoo movie comments and its
feedback.
Aspects of AO movies like:
3/27/2023 13
 diraamaa
 sagalee
 itti-fufinsa
 yeroo
 taatoo
 ergaa
 uffannaa
Scope and Limitation of Study…
 Aspect sentiment prediction:
 positive and negative
Supervised Machine learning techniques:
 Random Forest,
 Logistic Regression,
Support Vector Machine and
Multinomial Naïve Bayes
3/27/2023 14
Scope and Limitation of Study…
 In this ABSA, the following points have been
excluded:
Opinion holder
Time at which comment was posted
Likes, feedback opinion holder
Comparative opinion
Images, Emojis, audio and video
Texts other than Afaan Oromoo
Neutral sentiment polarity
3/27/2023 15
Significance of Study
 Business intelligence
Brand/ service insight
Competitive Analysis
Opinion Mining
Voice of Employee
Voice of Customer
Reputation management
Social media listening
3/27/2023 16
Summary of Related work
 Both national and international work on SA have
reviewed– ABSA with different ML techniques.
Summary of Amharic Related work
Summary of Afaan Oromoo Related work
3/27/2023 17
Research / Knowledge Gap
 To the best of our knowledge, in previous works
examined there was no work has been
done on Afaan Oromoo ABSA using machine
learning techniques.
The proposed work on the ABSA for Afaan
Oromoo movie reviews using machine learning
techniques is the first work and Original.
As a result, this research was attempted to cover
this gap in this investigation.
3/27/2023 18
Research Methodology
General Methodology followed
3/27/2023 19
Research Methodology…
Data Preprocessing
3/27/2023 20
Collecting AO
movie reviews
Removing
URL, Emojis
Removing
Punctuation
Normalization
Convert to
lowercase
AO stopword
Removal
Tokenization Stemming
Aspect term
extraction and
polarity prediction
Research Methodology…
Dataset Annotation
3/27/2023 21
Dataset
Annotation
Aspect Term
Extraction
Lexicon
based
Topic
modelling
Hand-crafted
lexicon
Aspect Polarity
prediction
Research Methodology…
Dataset Annotation…
Task 1:Aspect term extraction
Ex, “diraamaa baay’ee bareedaa dha; Garuu,
uffaannaan isaanii gaarii miti”.
Aspect Terms: {diraamaa, uffannaa}
3/27/2023 22
Research Methodology…
Dataset Annotation…
Task 1:Aspect term extraction
Ex2: “diraamaan baay’ee bareedaa dha; garuu maal
godhan baay’ee gabaabbate”.
Aspects Terns: {diraamaa, yeroo}
3/27/2023 23
Research Methodology…
Dataset Annotation…
Task 2:Aspect sentiment prediction
Ex1: “diraamaa baay’ee bareedaa dha; Garuu,
uffaannaan isaanii gaarii miti”.
Aspect polarity: {diraamaa, #positive, uffannaa,
#negative}
Ex2: “diraamaan baay’ee bareedaa dha; garuu
maal godhan baay’ee gabaabbate”.
Aspect Polarity: {diraamaa, #positive, yeroo,
#negative}
3/27/2023 24
Research Methodology…
Feature Vectorization
3/27/2023 25
Feature
Vectorizer
TFIDF
TfidfVectorizer
BOW
CountVectorizer
Research Methodology…
Implemented
Algorithms
Random Forest
Logistic
Regression
SVM and
MNB
Model Evaluation
Parameters
Accuracy,
 precision,
 recall
F1-score
3/27/2023 26
Research Methodology…
Proposed architecture
3/27/2023 27
Result and Discussion
Extracted Aspect term per reviews
3/27/2023 28
Result and Discussion…
Aspect term polarity prediction
3/27/2023 29
Result and Discussion…
3/27/2023 30
Models with feature selection
methods
Accuracy precision recall F1-score
Random Forest + BOW 88% 93% 90% 91%
Random Forest + TFIDF 88% 93% 89% 91%
Logistic Regression + BOW 87% 95% 87% 91%
Logistic Regression + TFIDF 87% 96% 87% 91%
SVM + BOW 87% 95% 86% 91%
SVM + TFIDF 88% 93% 90% 91%
MNB + BOW 88% 93% 90% 91%
MNB+TFIDF 88% 94% 88% 91%
Conclusion
SA is the field NLP which analysis the opinions
of reviewers to respective aspects of entity as
positive, negative or neutral.
SA has been studied in three levels:
Document level
Sentence level and
Aspect/feature based SA.
In this thesis, ABSA of Afaan Oromoo movie
reviews was investigated.
3/27/2023 31
Conclusion
In this thesis ABSA was investigated for Afaan
Oromoo movie reviews using:
 Random Forest,
Logistic regression,
SVM and MNB.
BoW and TFIDF was used in combination with
selected algorithms.
3/27/2023 32
Conclusion
The generated reports shows that almost all the
same evaluation parameters were generated by
using all proposed algorithms in combination with
both BOW and TFIDF.
The experimental results revealed that, the
classification report generated by all selected
algorithms have been found to be promising for
ABSA of AO movie reviews.
3/27/2023 33
Contribution
We have proposed the ABSA model for the Afaan Oromoo movie
reviews with good performance evaluation metrics.
We have built ABSA dataset by collecting 2800 Afaan Oromoo movie
reviews.
We came up with the guidelines to label the Afaan Oromoo ABSA
datasets for movie reviews.
The thesis can be used as a baseline for Aspect Based Sentiment-mining
related research works for opinionated Afaan Oromoo text.
3/27/2023 34
Recommendation
Points to be considered in future works are:
Emojis
Multi-class classification
Data from other social media
Standard dataset
Developing prototype
3/27/2023 35
Thank You for your
attention!!!
3/27/2023 36

Mais conteúdo relacionado

Mais procurados

Semantic interpretation
Semantic interpretationSemantic interpretation
Semantic interpretationVivek Kumar
 
Amazon sentimental analysis
Amazon sentimental analysisAmazon sentimental analysis
Amazon sentimental analysisAkhila
 
Pattern recognition and Machine Learning.
Pattern recognition and Machine Learning.Pattern recognition and Machine Learning.
Pattern recognition and Machine Learning.Rohit Kumar
 
Lecture Notes-Finite State Automata for NLP.pdf
Lecture Notes-Finite State Automata for NLP.pdfLecture Notes-Finite State Automata for NLP.pdf
Lecture Notes-Finite State Automata for NLP.pdfDeptii Chaudhari
 
Character Recognition using Machine Learning
Character Recognition using Machine LearningCharacter Recognition using Machine Learning
Character Recognition using Machine LearningRitwikSaurabh1
 
Sentiment analysis
Sentiment analysisSentiment analysis
Sentiment analysisAmenda Joy
 
Issues in knowledge representation
Issues in knowledge representationIssues in knowledge representation
Issues in knowledge representationSravanthi Emani
 
Project synopsis on online voting system
Project synopsis on online voting systemProject synopsis on online voting system
Project synopsis on online voting systemLhakpa Yangji
 
Computer vision suprim regmi
Computer vision suprim regmi Computer vision suprim regmi
Computer vision suprim regmi Suprim Regmi
 
Railways reservation system using socket programming
Railways reservation system using socket programmingRailways reservation system using socket programming
Railways reservation system using socket programmingUtkarsh Sharma
 
Sentiment Analysis
Sentiment AnalysisSentiment Analysis
Sentiment AnalysisAditya Nag
 
Introduction to Computer theory Daniel Cohen Chapter 2 Solutions
Introduction to Computer theory Daniel Cohen Chapter 2 SolutionsIntroduction to Computer theory Daniel Cohen Chapter 2 Solutions
Introduction to Computer theory Daniel Cohen Chapter 2 SolutionsAshu
 
Chapter 4 Embedded System: Application and Domain Specific
Chapter 4 Embedded System: Application and Domain SpecificChapter 4 Embedded System: Application and Domain Specific
Chapter 4 Embedded System: Application and Domain SpecificMoe Moe Myint
 
Intensity Transformation and Spatial filtering
Intensity Transformation and Spatial filteringIntensity Transformation and Spatial filtering
Intensity Transformation and Spatial filteringShajun Nisha
 
Sentiment analysis
Sentiment analysisSentiment analysis
Sentiment analysisSeher Can
 
Sentiment analysis presentation
Sentiment analysis presentationSentiment analysis presentation
Sentiment analysis presentationGunjanSrivastava23
 

Mais procurados (20)

Semantic interpretation
Semantic interpretationSemantic interpretation
Semantic interpretation
 
Amazon sentimental analysis
Amazon sentimental analysisAmazon sentimental analysis
Amazon sentimental analysis
 
Pattern recognition and Machine Learning.
Pattern recognition and Machine Learning.Pattern recognition and Machine Learning.
Pattern recognition and Machine Learning.
 
Lecture Notes-Finite State Automata for NLP.pdf
Lecture Notes-Finite State Automata for NLP.pdfLecture Notes-Finite State Automata for NLP.pdf
Lecture Notes-Finite State Automata for NLP.pdf
 
Character Recognition using Machine Learning
Character Recognition using Machine LearningCharacter Recognition using Machine Learning
Character Recognition using Machine Learning
 
Compiler lec 8
Compiler lec 8Compiler lec 8
Compiler lec 8
 
Sentiment analysis
Sentiment analysisSentiment analysis
Sentiment analysis
 
Issues in knowledge representation
Issues in knowledge representationIssues in knowledge representation
Issues in knowledge representation
 
Project synopsis on online voting system
Project synopsis on online voting systemProject synopsis on online voting system
Project synopsis on online voting system
 
1. peas
1. peas1. peas
1. peas
 
Mini Project presentation for MCA
Mini Project presentation for MCAMini Project presentation for MCA
Mini Project presentation for MCA
 
Computer vision suprim regmi
Computer vision suprim regmi Computer vision suprim regmi
Computer vision suprim regmi
 
Railways reservation system using socket programming
Railways reservation system using socket programmingRailways reservation system using socket programming
Railways reservation system using socket programming
 
Sentiment Analysis
Sentiment AnalysisSentiment Analysis
Sentiment Analysis
 
Distributed objects
Distributed objectsDistributed objects
Distributed objects
 
Introduction to Computer theory Daniel Cohen Chapter 2 Solutions
Introduction to Computer theory Daniel Cohen Chapter 2 SolutionsIntroduction to Computer theory Daniel Cohen Chapter 2 Solutions
Introduction to Computer theory Daniel Cohen Chapter 2 Solutions
 
Chapter 4 Embedded System: Application and Domain Specific
Chapter 4 Embedded System: Application and Domain SpecificChapter 4 Embedded System: Application and Domain Specific
Chapter 4 Embedded System: Application and Domain Specific
 
Intensity Transformation and Spatial filtering
Intensity Transformation and Spatial filteringIntensity Transformation and Spatial filtering
Intensity Transformation and Spatial filtering
 
Sentiment analysis
Sentiment analysisSentiment analysis
Sentiment analysis
 
Sentiment analysis presentation
Sentiment analysis presentationSentiment analysis presentation
Sentiment analysis presentation
 

Semelhante a Aspect Based Sentiment analysis of Afaan Oromoo Movie reviews using machine learning techniques

Analyzing Sentiment Of Movie Reviews In Bangla By Applying Machine Learning T...
Analyzing Sentiment Of Movie Reviews In Bangla By Applying Machine Learning T...Analyzing Sentiment Of Movie Reviews In Bangla By Applying Machine Learning T...
Analyzing Sentiment Of Movie Reviews In Bangla By Applying Machine Learning T...Andrew Parish
 
Movie recommendation system using collaborative filtering system
Movie recommendation system using collaborative filtering system Movie recommendation system using collaborative filtering system
Movie recommendation system using collaborative filtering system Mauryasuraj98
 
ENTERTAINMENT CONTENT RECOMMENDATION SYSTEM USING MACHINE LEARNING
ENTERTAINMENT CONTENT RECOMMENDATION SYSTEM USING MACHINE LEARNINGENTERTAINMENT CONTENT RECOMMENDATION SYSTEM USING MACHINE LEARNING
ENTERTAINMENT CONTENT RECOMMENDATION SYSTEM USING MACHINE LEARNINGIRJET Journal
 
IRJET- Searching an Optimal Algorithm for Movie Recommendation System
IRJET- Searching an Optimal Algorithm for Movie Recommendation SystemIRJET- Searching an Optimal Algorithm for Movie Recommendation System
IRJET- Searching an Optimal Algorithm for Movie Recommendation SystemIRJET Journal
 
IRJET- Sentimental Analysis for Students’ Feedback using Machine Learning App...
IRJET- Sentimental Analysis for Students’ Feedback using Machine Learning App...IRJET- Sentimental Analysis for Students’ Feedback using Machine Learning App...
IRJET- Sentimental Analysis for Students’ Feedback using Machine Learning App...IRJET Journal
 
IRJET- Sentimental Analysis on Audio and Video
IRJET- Sentimental Analysis on Audio and VideoIRJET- Sentimental Analysis on Audio and Video
IRJET- Sentimental Analysis on Audio and VideoIRJET Journal
 
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...IRJET Journal
 
AN EXPERIMENTAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MINING
AN EXPERIMENTAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MININGAN EXPERIMENTAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MINING
AN EXPERIMENTAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MININGijscai
 
Phase_1_ppt.pptx
Phase_1_ppt.pptxPhase_1_ppt.pptx
Phase_1_ppt.pptxbharatt7
 
A Survey On Sentiment Analysis Of Movie Reviews
A Survey On Sentiment Analysis Of Movie ReviewsA Survey On Sentiment Analysis Of Movie Reviews
A Survey On Sentiment Analysis Of Movie ReviewsShannon Green
 
IRJET - Enhanced Movie Recommendation Engine using Content Filtering, Collabo...
IRJET - Enhanced Movie Recommendation Engine using Content Filtering, Collabo...IRJET - Enhanced Movie Recommendation Engine using Content Filtering, Collabo...
IRJET - Enhanced Movie Recommendation Engine using Content Filtering, Collabo...IRJET Journal
 
Data Analysis Section
Data Analysis SectionData Analysis Section
Data Analysis SectionBrett Combs
 
Recommendation System using Machine Learning Techniques
Recommendation System using Machine Learning TechniquesRecommendation System using Machine Learning Techniques
Recommendation System using Machine Learning TechniquesIRJET Journal
 
The sarcasm detection with the method of logistic regression
The sarcasm detection with the method of logistic regressionThe sarcasm detection with the method of logistic regression
The sarcasm detection with the method of logistic regressionEditorIJAERD
 
Analyzing sentiment system to specify polarity by lexicon-based
Analyzing sentiment system to specify polarity by lexicon-basedAnalyzing sentiment system to specify polarity by lexicon-based
Analyzing sentiment system to specify polarity by lexicon-basedjournalBEEI
 
An Experimental Study of Feature Extraction Techniques in Opinion Mining
An Experimental Study of Feature Extraction Techniques in Opinion MiningAn Experimental Study of Feature Extraction Techniques in Opinion Mining
An Experimental Study of Feature Extraction Techniques in Opinion MiningIJSCAI Journal
 
An experimental study of feature
An experimental study of featureAn experimental study of feature
An experimental study of featureijscai
 
Mining of product reviews at aspect level
Mining of product reviews at aspect levelMining of product reviews at aspect level
Mining of product reviews at aspect levelijfcstjournal
 

Semelhante a Aspect Based Sentiment analysis of Afaan Oromoo Movie reviews using machine learning techniques (20)

Analyzing Sentiment Of Movie Reviews In Bangla By Applying Machine Learning T...
Analyzing Sentiment Of Movie Reviews In Bangla By Applying Machine Learning T...Analyzing Sentiment Of Movie Reviews In Bangla By Applying Machine Learning T...
Analyzing Sentiment Of Movie Reviews In Bangla By Applying Machine Learning T...
 
Movie recommendation system using collaborative filtering system
Movie recommendation system using collaborative filtering system Movie recommendation system using collaborative filtering system
Movie recommendation system using collaborative filtering system
 
ENTERTAINMENT CONTENT RECOMMENDATION SYSTEM USING MACHINE LEARNING
ENTERTAINMENT CONTENT RECOMMENDATION SYSTEM USING MACHINE LEARNINGENTERTAINMENT CONTENT RECOMMENDATION SYSTEM USING MACHINE LEARNING
ENTERTAINMENT CONTENT RECOMMENDATION SYSTEM USING MACHINE LEARNING
 
IRJET- Searching an Optimal Algorithm for Movie Recommendation System
IRJET- Searching an Optimal Algorithm for Movie Recommendation SystemIRJET- Searching an Optimal Algorithm for Movie Recommendation System
IRJET- Searching an Optimal Algorithm for Movie Recommendation System
 
IRJET- Sentimental Analysis for Students’ Feedback using Machine Learning App...
IRJET- Sentimental Analysis for Students’ Feedback using Machine Learning App...IRJET- Sentimental Analysis for Students’ Feedback using Machine Learning App...
IRJET- Sentimental Analysis for Students’ Feedback using Machine Learning App...
 
Ijetcas14 480
Ijetcas14 480Ijetcas14 480
Ijetcas14 480
 
IRJET- Sentimental Analysis on Audio and Video
IRJET- Sentimental Analysis on Audio and VideoIRJET- Sentimental Analysis on Audio and Video
IRJET- Sentimental Analysis on Audio and Video
 
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
IRJET- Sentimental Analysis on Audio and Video using Vader Algorithm -Monali ...
 
AN EXPERIMENTAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MINING
AN EXPERIMENTAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MININGAN EXPERIMENTAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MINING
AN EXPERIMENTAL STUDY OF FEATURE EXTRACTION TECHNIQUES IN OPINION MINING
 
Phase_1_ppt.pptx
Phase_1_ppt.pptxPhase_1_ppt.pptx
Phase_1_ppt.pptx
 
A Survey On Sentiment Analysis Of Movie Reviews
A Survey On Sentiment Analysis Of Movie ReviewsA Survey On Sentiment Analysis Of Movie Reviews
A Survey On Sentiment Analysis Of Movie Reviews
 
Estimating the overall sentiment score by inferring modus ponens law
Estimating the overall sentiment score by inferring modus ponens lawEstimating the overall sentiment score by inferring modus ponens law
Estimating the overall sentiment score by inferring modus ponens law
 
IRJET - Enhanced Movie Recommendation Engine using Content Filtering, Collabo...
IRJET - Enhanced Movie Recommendation Engine using Content Filtering, Collabo...IRJET - Enhanced Movie Recommendation Engine using Content Filtering, Collabo...
IRJET - Enhanced Movie Recommendation Engine using Content Filtering, Collabo...
 
Data Analysis Section
Data Analysis SectionData Analysis Section
Data Analysis Section
 
Recommendation System using Machine Learning Techniques
Recommendation System using Machine Learning TechniquesRecommendation System using Machine Learning Techniques
Recommendation System using Machine Learning Techniques
 
The sarcasm detection with the method of logistic regression
The sarcasm detection with the method of logistic regressionThe sarcasm detection with the method of logistic regression
The sarcasm detection with the method of logistic regression
 
Analyzing sentiment system to specify polarity by lexicon-based
Analyzing sentiment system to specify polarity by lexicon-basedAnalyzing sentiment system to specify polarity by lexicon-based
Analyzing sentiment system to specify polarity by lexicon-based
 
An Experimental Study of Feature Extraction Techniques in Opinion Mining
An Experimental Study of Feature Extraction Techniques in Opinion MiningAn Experimental Study of Feature Extraction Techniques in Opinion Mining
An Experimental Study of Feature Extraction Techniques in Opinion Mining
 
An experimental study of feature
An experimental study of featureAn experimental study of feature
An experimental study of feature
 
Mining of product reviews at aspect level
Mining of product reviews at aspect levelMining of product reviews at aspect level
Mining of product reviews at aspect level
 

Último

08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsRoshan Dwivedi
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 

Último (20)

08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 

Aspect Based Sentiment analysis of Afaan Oromoo Movie reviews using machine learning techniques

  • 1. BULE HORA UNIVERSITY COLLEGE OF INFORMATICS COMPUTER SCIENCE DEPARTMENT Aspect Based Sentiment Analysis of Afaan Oromoo Movie Reviews Using Machine Learning Techniques By Obsa Gelchu Advisor: Kula kekeba (PhD)
  • 2. Presentation Outline Introduction Statements of Problem Research Questions  Objective of the study Scope and Limitation Significance of the Study Summary of Related work Research Gap Research Methodology Experimental Results and Discussion Conclusion, Contribution and Recommendation 3/27/2023 2
  • 3. Introduction Sentiment Analysis (SA) SA is increasingly viewed as vital task both from academic and commercial stand point. Basically, SA is NLP techniques used to identify and categorize attitude of reviewers to respective topics as positive, negative, or neutral. 3/27/2023 3
  • 4. Introduction… Levels of Sentiment Analysis 3/27/2023 4 Sentiment Analysis Document level Sentence level Aspect level
  • 5. Introduction…  Document level and Sentence level SA Considered overall polarity of the reviewed text regardless attributes of an entity.  However, Comments of the reviewer may contain different aspects/features. Ex: “The story of the movie is good but the acting of the actors is awful”. Aspect terms: {message, acting} Aspect Polarity: {message, #positive, acting, #negative} 5
  • 6. Introduction… Aspect Based Sentiment Analysis (ABSA) ABSA is sub-level of SA which extracts aspect of each topic from reviewer sentence with its corresponding sentiment polarity. Ex: “The actor is so good, but this movie just horrible”. Aspect terms: {actor, movie } Aspect polarity: {actor, #positive , movie, #negative} 3/27/2023 6
  • 7. Statement of the Problem With the emergency of social media, comments to particular entity in business industry are increasing daily from the behalf of users/customers. Opinions can influence the thinking of human beings as humans always want to know the opinions of others in every decision they may made. 3/27/2023 7
  • 8. Statement of the Problem… To summarize thousands opinions of users to respective topics, different scholars were investigated SA only at document and sentence level regardless of its features. Comments of the users may contain different aspects/features. Ex: “The actor is so good, but this movie just horrible”. Aspect terms: {actor, movie} 3/27/2023 8
  • 9. Statement of the Problem … Analyzing opinion of reviewers only at document and sentence level SA cannot provide sufficient information. To analyse the opinions of customers at fine- grained level, ABSA was proposed to analyse Afaan Oromoo movie reviews using machine learning techniques. 3/27/2023 9
  • 10. Research Questions 1. Which Machine learning model is most appropriate for Afaan Oromoo ABSA for movie reviews? 2. What are the best attributes for Afaan Oromoo movie reviews for ABSA? 3. What are the main challenges in building Afaan Oromoo ABSA dataset for movie reviews? 4. What is the performance of the proposed ABSA system? 3/27/2023 10
  • 11. Objectives  General objective To design and develop ABSA model for Afaan Oromoo movie reviews using machine learning techniques. Specific Objectives To review SA related work for ABSA of AO movie reviews. To investigate appropriate strategies to prepare ABSA dataset for Afaan Oromoo movie reviews. To explore how aspect-based opinions could be designed and implemented for Afaan Oromoo movie entertainment. 3/27/2023 11
  • 12. Objectives… Specific Objectives…. To develop different machine learning models for Afaan Oromoo ABSA for movie reviews. To evaluate the performance of the proposed models for Afaan Oromoo movie reviews. To prepare Afaan Oromoo ABSA dataset for movie reviews. Based on the gained result, to propose a set of improvements and to suggest recommendations. 3/27/2023 12
  • 13. Scope and Limitation of Study The objective of the study is to design and develop ABSA model for Afaan Oromoo movie reviews using machine learning techniques. For this purpose we have focused on:  Afaan Oromoo movie comments and its feedback. Aspects of AO movies like: 3/27/2023 13  diraamaa  sagalee  itti-fufinsa  yeroo  taatoo  ergaa  uffannaa
  • 14. Scope and Limitation of Study…  Aspect sentiment prediction:  positive and negative Supervised Machine learning techniques:  Random Forest,  Logistic Regression, Support Vector Machine and Multinomial Naïve Bayes 3/27/2023 14
  • 15. Scope and Limitation of Study…  In this ABSA, the following points have been excluded: Opinion holder Time at which comment was posted Likes, feedback opinion holder Comparative opinion Images, Emojis, audio and video Texts other than Afaan Oromoo Neutral sentiment polarity 3/27/2023 15
  • 16. Significance of Study  Business intelligence Brand/ service insight Competitive Analysis Opinion Mining Voice of Employee Voice of Customer Reputation management Social media listening 3/27/2023 16
  • 17. Summary of Related work  Both national and international work on SA have reviewed– ABSA with different ML techniques. Summary of Amharic Related work Summary of Afaan Oromoo Related work 3/27/2023 17
  • 18. Research / Knowledge Gap  To the best of our knowledge, in previous works examined there was no work has been done on Afaan Oromoo ABSA using machine learning techniques. The proposed work on the ABSA for Afaan Oromoo movie reviews using machine learning techniques is the first work and Original. As a result, this research was attempted to cover this gap in this investigation. 3/27/2023 18
  • 20. Research Methodology… Data Preprocessing 3/27/2023 20 Collecting AO movie reviews Removing URL, Emojis Removing Punctuation Normalization Convert to lowercase AO stopword Removal Tokenization Stemming Aspect term extraction and polarity prediction
  • 21. Research Methodology… Dataset Annotation 3/27/2023 21 Dataset Annotation Aspect Term Extraction Lexicon based Topic modelling Hand-crafted lexicon Aspect Polarity prediction
  • 22. Research Methodology… Dataset Annotation… Task 1:Aspect term extraction Ex, “diraamaa baay’ee bareedaa dha; Garuu, uffaannaan isaanii gaarii miti”. Aspect Terms: {diraamaa, uffannaa} 3/27/2023 22
  • 23. Research Methodology… Dataset Annotation… Task 1:Aspect term extraction Ex2: “diraamaan baay’ee bareedaa dha; garuu maal godhan baay’ee gabaabbate”. Aspects Terns: {diraamaa, yeroo} 3/27/2023 23
  • 24. Research Methodology… Dataset Annotation… Task 2:Aspect sentiment prediction Ex1: “diraamaa baay’ee bareedaa dha; Garuu, uffaannaan isaanii gaarii miti”. Aspect polarity: {diraamaa, #positive, uffannaa, #negative} Ex2: “diraamaan baay’ee bareedaa dha; garuu maal godhan baay’ee gabaabbate”. Aspect Polarity: {diraamaa, #positive, yeroo, #negative} 3/27/2023 24
  • 25. Research Methodology… Feature Vectorization 3/27/2023 25 Feature Vectorizer TFIDF TfidfVectorizer BOW CountVectorizer
  • 26. Research Methodology… Implemented Algorithms Random Forest Logistic Regression SVM and MNB Model Evaluation Parameters Accuracy,  precision,  recall F1-score 3/27/2023 26
  • 28. Result and Discussion Extracted Aspect term per reviews 3/27/2023 28
  • 29. Result and Discussion… Aspect term polarity prediction 3/27/2023 29
  • 30. Result and Discussion… 3/27/2023 30 Models with feature selection methods Accuracy precision recall F1-score Random Forest + BOW 88% 93% 90% 91% Random Forest + TFIDF 88% 93% 89% 91% Logistic Regression + BOW 87% 95% 87% 91% Logistic Regression + TFIDF 87% 96% 87% 91% SVM + BOW 87% 95% 86% 91% SVM + TFIDF 88% 93% 90% 91% MNB + BOW 88% 93% 90% 91% MNB+TFIDF 88% 94% 88% 91%
  • 31. Conclusion SA is the field NLP which analysis the opinions of reviewers to respective aspects of entity as positive, negative or neutral. SA has been studied in three levels: Document level Sentence level and Aspect/feature based SA. In this thesis, ABSA of Afaan Oromoo movie reviews was investigated. 3/27/2023 31
  • 32. Conclusion In this thesis ABSA was investigated for Afaan Oromoo movie reviews using:  Random Forest, Logistic regression, SVM and MNB. BoW and TFIDF was used in combination with selected algorithms. 3/27/2023 32
  • 33. Conclusion The generated reports shows that almost all the same evaluation parameters were generated by using all proposed algorithms in combination with both BOW and TFIDF. The experimental results revealed that, the classification report generated by all selected algorithms have been found to be promising for ABSA of AO movie reviews. 3/27/2023 33
  • 34. Contribution We have proposed the ABSA model for the Afaan Oromoo movie reviews with good performance evaluation metrics. We have built ABSA dataset by collecting 2800 Afaan Oromoo movie reviews. We came up with the guidelines to label the Afaan Oromoo ABSA datasets for movie reviews. The thesis can be used as a baseline for Aspect Based Sentiment-mining related research works for opinionated Afaan Oromoo text. 3/27/2023 34
  • 35. Recommendation Points to be considered in future works are: Emojis Multi-class classification Data from other social media Standard dataset Developing prototype 3/27/2023 35
  • 36. Thank You for your attention!!! 3/27/2023 36