SlideShare a Scribd company logo
A Fuzzy Approach For Multi-Domain
Sentiment Analysis
Mauro Dragoni
Fondazione Bruno Kessler (FBK), Shape and Evolve Living Knowledge Unit (SHELL)
https://shell.fbk.eu/index.php/Mauro_Dragoni - dragoni@fbk.eu
work done in collaboration with
Prof. Andrea G.B. Tettamanzi and Prof. Celia da Costa Pereira
INRIA Sophia Antipolis
June, 19th 2014
Outline
1. Background on Sentiment Analysis and Fuzzy Logic
2. Motivations
3. The Approach
4. Evaluation of the Implemented System
Sentiment Analysis - 1
 Natural Language Processing task for identifying the opinion given by
someone with respect to something.
 Opinions may be positive, negative, or neutral.
 The value associated with the opinion is called “polarity”.
Sentiment Analysis - 2
 Basic challenges:
 Identification of the polarities for each term in the text.
 Deciding how to aggregate the different polarities.
 Advanced challenges:
 Identification of the entities in each sentence (subjects).
 Identification of the features describing each entity.
 Adaptation of the sentiment model to different domain.
 Manage the uncertainty of each learned information within the single domain
Fuzzy Logic
 Allows to represent imprecise information.
 With respect to classical logic, truth-values of assertions may assume all
values in the interval [0, 1]
 The main element of the fuzzy logic are Fuzzy Sets
Hot temperature.
x
y
Motivations - 1
 The same concept may have different polarities in different domains.
 The polarity associating a concept to a domain may be uncertain due to
the different contexts in which it is used.
Motivations - 2
 The assignment of a unique polarity value to the entire text leads to
imprecise information.
 In the same text, different aspects have to be analyzed.
 A significant concept extraction capability is required.
“I bought a new smartphone: the screen is awesome, even if some
colors are not very brilliant, but the battery is too short”
The Approach
 Creation of the knowledge base.
 Concept extraction.
 Learning of the preliminary sentiment information.
 Propagation of the learned information through the knowledge graph.
 Modeling of the fuzzy shapes.
Creation of the Knowledge Base
 Based on the integration of WordNet with SenticNet
 WordNet has been enriched with terms extracted from the Roget’s
Thesaurus
 The links between WordNet and SenticNet have been built by taking into
account the synonyms of each WordNet synset and the synonyms of each
SenticNet concept.
 In order to avoid ambiguities not all associations have been created.
 Example: concept “base”
WordNet: 20 senses (for the noun)
SenticNet: base (beneath, below, understructure)  WordNet sense 2
Concept Extraction - 1
 Two samples:
1. Today I went to the mall and bought some desserts and a lot of very nice
Christmas gifts.
2. The touchscreen is awesome but the battery is too short.
Concept Extraction - 2
Multi-Domain Fuzzy Propagation - 1
 Polarity information is propagated through the knowledge base by using
an algorithm implementing the simulated annealing strategy.
 The propagation of the values is driven by three parameters: annealing
rate, propagation rate, and convergence limit.
 The intermediate polarity values measured on each concept at the end of
each iteration are stored in order to build the final fuzzy shape associated
with each combination concept-domain.
 A different model is learned for each domain.
Multi-Domain Fuzzy Propagation - 2
Domain Initialization:
Information Propagation:
Stop Condition:
Multi-Domain Fuzzy Propagation - 3
 Trade-offs:
 high propagation rate  risk of polarity convergence
 low convergence limit  risk of polarity convergence
 lower propagation rate  incomplete graph
 high annealing rate  premature stop of the algorithm
 high convergence limit  premature stop of the algorithm
Multi-Domain Fuzzy Propagation - 4
Modeling of Fuzzy Shapes - 1
Value computed from the
training set.
Value obtained after the
propagation phase.
Support computed based on the
variance value.
Modeling of Fuzzy Shapes - 2
Type 1 level of uncertainty: the core
of the fuzzy trapezoid crosses the
neutral polarity
Type 2 level of uncertainty: only the
support of the fuzzy trapezoid crosses
the neutral polarity
Evaluation of the System - 1
 Evaluation on the Blitzer dataset:
 25 domains
 ~3000 reviews for each domain in the balanced dataset
 75% of instances for the training, 25% for the validation
 Three baselines: SVM, Max-Entropy, and Naïve-Bayes
 Compared the performance by discarding the different levels of uncertainty
 Evaluation on:
 Elementary Polarity Computation
 Concept Extraction + Polarity Computation
Evaluation of the System - 2
 How fuzzy polarities are aggregated?
x
Evaluation of the System - 3
Evaluation of the System - 4
Approach Avg. Precision Avg. Recall
SVM 0.8068 1.0
Naïve-Bayes 0.8227 1.0
Max-Entropy 0.8225 1.0
MDFSA 0.8617 ~ 1.0
MDFSA
(Type 1 Uncertainty excluded)
0.8735 ~ 0.7
MDFSA
(Type 1 & 2 Uncertainty excluded)
0.8991 ~ 0.5
Elementary Polarity Computation:
Evaluation of the System - 5
Approach Precision Recall F-Measure
MDFSA 0.25 0.26 0.25
IBM 0.24 0.14 0.18
UNI-NEGEV 0.12 0.05 0.07
Concept Extraction + Polarity Computation (ESWC 2014 Challenge):
Future Work
 Integration of more knowledge bases into the system.
 Improve how ambiguities are addressed.
 Improve the concept extraction module.
 Extending the approach for addressing multilingualism.
 Apply the approach to the social network environment.
Mauro Dragoni
https://shell.fbk.eu/index.php/Mauro_Dragoni
dragoni@fbk.eu

More Related Content

What's hot

Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
Sujit Pal
 
Neural Networks and Deep Learning
Neural Networks and Deep LearningNeural Networks and Deep Learning
Neural Networks and Deep Learning
Asim Jalis
 
55
5555
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningLior Rokach
 
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling MethodsContextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Neal Lathia
 
An Introduction to Deep Learning (April 2018)
An Introduction to Deep Learning (April 2018)An Introduction to Deep Learning (April 2018)
An Introduction to Deep Learning (April 2018)
Julien SIMON
 
BREAKING MIGNOTTE’S SEQUENCE BASED SECRET SHARING SCHEME USING SMT SOLVER
BREAKING MIGNOTTE’S SEQUENCE BASED SECRET SHARING SCHEME USING SMT SOLVERBREAKING MIGNOTTE’S SEQUENCE BASED SECRET SHARING SCHEME USING SMT SOLVER
BREAKING MIGNOTTE’S SEQUENCE BASED SECRET SHARING SCHEME USING SMT SOLVER
ijcsit
 
An introduction to Machine Learning
An introduction to Machine LearningAn introduction to Machine Learning
An introduction to Machine Learningbutest
 
Eswc2009
Eswc2009Eswc2009
Eswc2009fanizzi
 
Soft computing abstracts
Soft computing abstractsSoft computing abstracts
Soft computing abstractsabctry
 
Sentiment Analysis on Twitter
Sentiment Analysis on TwitterSentiment Analysis on Twitter
Sentiment Analysis on Twitter
Subarno Pal
 
Generating Natural-Language Text with Neural Networks
Generating Natural-Language Text with Neural NetworksGenerating Natural-Language Text with Neural Networks
Generating Natural-Language Text with Neural Networks
Jonathan Mugan
 
Unsupervised Cross-Domain Image Generation
Unsupervised Cross-Domain Image GenerationUnsupervised Cross-Domain Image Generation
Unsupervised Cross-Domain Image Generation
Junho Cho
 
PRACTICAL ADVERSARIAL ATTACKS AGAINST CHALLENGING MODELS ENVIRONMENTS - Moust...
PRACTICAL ADVERSARIAL ATTACKS AGAINST CHALLENGING MODELS ENVIRONMENTS - Moust...PRACTICAL ADVERSARIAL ATTACKS AGAINST CHALLENGING MODELS ENVIRONMENTS - Moust...
PRACTICAL ADVERSARIAL ATTACKS AGAINST CHALLENGING MODELS ENVIRONMENTS - Moust...
GeekPwn Keen
 
The Smart Way To Invest in AI and ML_SFStartupDay
The Smart Way To Invest in AI and ML_SFStartupDayThe Smart Way To Invest in AI and ML_SFStartupDay
The Smart Way To Invest in AI and ML_SFStartupDay
Amazon Web Services
 
CP2083 Introduction to Artificial Intelligence
CP2083 Introduction to Artificial IntelligenceCP2083 Introduction to Artificial Intelligence
CP2083 Introduction to Artificial Intelligencebutest
 
Deep learning in Crypto Currency Trading
Deep learning in Crypto Currency TradingDeep learning in Crypto Currency Trading
Deep learning in Crypto Currency Trading
Martin Kariithi, CFA
 

What's hot (17)

Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
 
Neural Networks and Deep Learning
Neural Networks and Deep LearningNeural Networks and Deep Learning
Neural Networks and Deep Learning
 
55
5555
55
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling MethodsContextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
 
An Introduction to Deep Learning (April 2018)
An Introduction to Deep Learning (April 2018)An Introduction to Deep Learning (April 2018)
An Introduction to Deep Learning (April 2018)
 
BREAKING MIGNOTTE’S SEQUENCE BASED SECRET SHARING SCHEME USING SMT SOLVER
BREAKING MIGNOTTE’S SEQUENCE BASED SECRET SHARING SCHEME USING SMT SOLVERBREAKING MIGNOTTE’S SEQUENCE BASED SECRET SHARING SCHEME USING SMT SOLVER
BREAKING MIGNOTTE’S SEQUENCE BASED SECRET SHARING SCHEME USING SMT SOLVER
 
An introduction to Machine Learning
An introduction to Machine LearningAn introduction to Machine Learning
An introduction to Machine Learning
 
Eswc2009
Eswc2009Eswc2009
Eswc2009
 
Soft computing abstracts
Soft computing abstractsSoft computing abstracts
Soft computing abstracts
 
Sentiment Analysis on Twitter
Sentiment Analysis on TwitterSentiment Analysis on Twitter
Sentiment Analysis on Twitter
 
Generating Natural-Language Text with Neural Networks
Generating Natural-Language Text with Neural NetworksGenerating Natural-Language Text with Neural Networks
Generating Natural-Language Text with Neural Networks
 
Unsupervised Cross-Domain Image Generation
Unsupervised Cross-Domain Image GenerationUnsupervised Cross-Domain Image Generation
Unsupervised Cross-Domain Image Generation
 
PRACTICAL ADVERSARIAL ATTACKS AGAINST CHALLENGING MODELS ENVIRONMENTS - Moust...
PRACTICAL ADVERSARIAL ATTACKS AGAINST CHALLENGING MODELS ENVIRONMENTS - Moust...PRACTICAL ADVERSARIAL ATTACKS AGAINST CHALLENGING MODELS ENVIRONMENTS - Moust...
PRACTICAL ADVERSARIAL ATTACKS AGAINST CHALLENGING MODELS ENVIRONMENTS - Moust...
 
The Smart Way To Invest in AI and ML_SFStartupDay
The Smart Way To Invest in AI and ML_SFStartupDayThe Smart Way To Invest in AI and ML_SFStartupDay
The Smart Way To Invest in AI and ML_SFStartupDay
 
CP2083 Introduction to Artificial Intelligence
CP2083 Introduction to Artificial IntelligenceCP2083 Introduction to Artificial Intelligence
CP2083 Introduction to Artificial Intelligence
 
Deep learning in Crypto Currency Trading
Deep learning in Crypto Currency TradingDeep learning in Crypto Currency Trading
Deep learning in Crypto Currency Trading
 

Viewers also liked

i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approachi.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
Jonathan Josue Cid Galiot
 
Data mining project
Data mining projectData mining project
Data mining project
Shweta_Kamble
 
Sentiment mining- The Design and Implementation of an Internet Public Opinion...
Sentiment mining- The Design and Implementation of an Internet PublicOpinion...Sentiment mining- The Design and Implementation of an Internet PublicOpinion...
Sentiment mining- The Design and Implementation of an Internet Public Opinion...
Prateek Singh
 
Mike davies sentiment_analysis_presentation_backup
Mike davies sentiment_analysis_presentation_backupMike davies sentiment_analysis_presentation_backup
Mike davies sentiment_analysis_presentation_backup
m1ked
 
Machine Learning - Object Detection and Classification
Machine Learning - Object Detection and ClassificationMachine Learning - Object Detection and Classification
Machine Learning - Object Detection and Classification
Vikas Jain
 
Sentiment Analysis in Twitter
Sentiment Analysis in TwitterSentiment Analysis in Twitter
Sentiment Analysis in Twitter
prnk08
 
Sentiment Analysis in Twitter with Lightweight Discourse Analysis
Sentiment Analysis in Twitter with Lightweight Discourse AnalysisSentiment Analysis in Twitter with Lightweight Discourse Analysis
Sentiment Analysis in Twitter with Lightweight Discourse Analysis
Subhabrata Mukherjee
 
Twitter sentiment analysis
Twitter sentiment analysisTwitter sentiment analysis
Twitter sentiment analysis
Sunil Kandari
 
Project prSentiment Analysis of Twitter Data Using Machine Learning Approach...
Project prSentiment Analysis  of Twitter Data Using Machine Learning Approach...Project prSentiment Analysis  of Twitter Data Using Machine Learning Approach...
Project prSentiment Analysis of Twitter Data Using Machine Learning Approach...
Geetika Gautam
 
Arabic Text mining Classification
Arabic Text mining Classification Arabic Text mining Classification
Arabic Text mining Classification Zakaria Zubi
 
Sentiment tool Project presentaion
Sentiment tool Project presentaionSentiment tool Project presentaion
Sentiment tool Project presentaion
Ravindra Chaudhary
 
Sentiment Analaysis on Twitter
Sentiment Analaysis on TwitterSentiment Analaysis on Twitter
Sentiment Analaysis on Twitter
Nitish J Prabhu
 
Sentiment analysis of arabic,a survey
Sentiment analysis of arabic,a surveySentiment analysis of arabic,a survey
Sentiment analysis of arabic,a surveyArabic_NLP_ImamU2013
 
Tweets Classification using Naive Bayes and SVM
Tweets Classification using Naive Bayes and SVMTweets Classification using Naive Bayes and SVM
Tweets Classification using Naive Bayes and SVM
Trilok Sharma
 
Sentiment analysis using naive bayes classifier
Sentiment analysis using naive bayes classifier Sentiment analysis using naive bayes classifier
Sentiment analysis using naive bayes classifier
Dev Sahu
 
Introduction to Sentiment Analysis
Introduction to Sentiment AnalysisIntroduction to Sentiment Analysis
Introduction to Sentiment Analysis
Jaganadh Gopinadhan
 
Building Large Arabic Multi-Domain Resources for Sentiment Analysis
Building Large Arabic Multi-Domain Resources for Sentiment Analysis Building Large Arabic Multi-Domain Resources for Sentiment Analysis
Building Large Arabic Multi-Domain Resources for Sentiment Analysis
Hady Elsahar
 
Sentiment analysis of twitter data
Sentiment analysis of twitter dataSentiment analysis of twitter data
Sentiment analysis of twitter data
Bhagyashree Deokar
 
[ASA] Sentiment Analysis in Twitter, a Study on the Saudi Community
[ASA] Sentiment Analysis in Twitter, a Study on the Saudi Community[ASA] Sentiment Analysis in Twitter, a Study on the Saudi Community
[ASA] Sentiment Analysis in Twitter, a Study on the Saudi Community
ASA_Group
 

Viewers also liked (20)

i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approachi.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
i.a.Preoperative ovarian cancer diagnosis using neuro fuzzy approach
 
Data mining project
Data mining projectData mining project
Data mining project
 
Sentiment mining- The Design and Implementation of an Internet Public Opinion...
Sentiment mining- The Design and Implementation of an Internet PublicOpinion...Sentiment mining- The Design and Implementation of an Internet PublicOpinion...
Sentiment mining- The Design and Implementation of an Internet Public Opinion...
 
Mike davies sentiment_analysis_presentation_backup
Mike davies sentiment_analysis_presentation_backupMike davies sentiment_analysis_presentation_backup
Mike davies sentiment_analysis_presentation_backup
 
Machine Learning - Object Detection and Classification
Machine Learning - Object Detection and ClassificationMachine Learning - Object Detection and Classification
Machine Learning - Object Detection and Classification
 
Sentiment Analysis in Twitter
Sentiment Analysis in TwitterSentiment Analysis in Twitter
Sentiment Analysis in Twitter
 
Sentiment Analysis in Twitter with Lightweight Discourse Analysis
Sentiment Analysis in Twitter with Lightweight Discourse AnalysisSentiment Analysis in Twitter with Lightweight Discourse Analysis
Sentiment Analysis in Twitter with Lightweight Discourse Analysis
 
Twitter sentiment analysis
Twitter sentiment analysisTwitter sentiment analysis
Twitter sentiment analysis
 
Project prSentiment Analysis of Twitter Data Using Machine Learning Approach...
Project prSentiment Analysis  of Twitter Data Using Machine Learning Approach...Project prSentiment Analysis  of Twitter Data Using Machine Learning Approach...
Project prSentiment Analysis of Twitter Data Using Machine Learning Approach...
 
Arabic Text mining Classification
Arabic Text mining Classification Arabic Text mining Classification
Arabic Text mining Classification
 
Arabic tokenization and stemming
Arabic tokenization and  stemmingArabic tokenization and  stemming
Arabic tokenization and stemming
 
Sentiment tool Project presentaion
Sentiment tool Project presentaionSentiment tool Project presentaion
Sentiment tool Project presentaion
 
Sentiment Analaysis on Twitter
Sentiment Analaysis on TwitterSentiment Analaysis on Twitter
Sentiment Analaysis on Twitter
 
Sentiment analysis of arabic,a survey
Sentiment analysis of arabic,a surveySentiment analysis of arabic,a survey
Sentiment analysis of arabic,a survey
 
Tweets Classification using Naive Bayes and SVM
Tweets Classification using Naive Bayes and SVMTweets Classification using Naive Bayes and SVM
Tweets Classification using Naive Bayes and SVM
 
Sentiment analysis using naive bayes classifier
Sentiment analysis using naive bayes classifier Sentiment analysis using naive bayes classifier
Sentiment analysis using naive bayes classifier
 
Introduction to Sentiment Analysis
Introduction to Sentiment AnalysisIntroduction to Sentiment Analysis
Introduction to Sentiment Analysis
 
Building Large Arabic Multi-Domain Resources for Sentiment Analysis
Building Large Arabic Multi-Domain Resources for Sentiment Analysis Building Large Arabic Multi-Domain Resources for Sentiment Analysis
Building Large Arabic Multi-Domain Resources for Sentiment Analysis
 
Sentiment analysis of twitter data
Sentiment analysis of twitter dataSentiment analysis of twitter data
Sentiment analysis of twitter data
 
[ASA] Sentiment Analysis in Twitter, a Study on the Saudi Community
[ASA] Sentiment Analysis in Twitter, a Study on the Saudi Community[ASA] Sentiment Analysis in Twitter, a Study on the Saudi Community
[ASA] Sentiment Analysis in Twitter, a Study on the Saudi Community
 

Similar to A Fuzzy Approach For Multi-Domain Sentiment Analysis

Deep learning tutorial 9/2019
Deep learning tutorial 9/2019Deep learning tutorial 9/2019
Deep learning tutorial 9/2019
Amr Rashed
 
Deep Learning Tutorial
Deep Learning TutorialDeep Learning Tutorial
Deep Learning Tutorial
Amr Rashed
 
soft computing BTU MCA 3rd SEM unit 1 .pptx
soft computing BTU MCA 3rd SEM unit 1 .pptxsoft computing BTU MCA 3rd SEM unit 1 .pptx
soft computing BTU MCA 3rd SEM unit 1 .pptx
naveen356604
 
Methodological study of opinion mining and sentiment analysis techniques
Methodological study of opinion mining and sentiment analysis techniquesMethodological study of opinion mining and sentiment analysis techniques
Methodological study of opinion mining and sentiment analysis techniques
ijsc
 
LearningAG.ppt
LearningAG.pptLearningAG.ppt
LearningAG.pptbutest
 
Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Big Data Intelligence: from Correlation Discovery to Causal Reasoning Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Wanjin Yu
 
Brief Tour of Machine Learning
Brief Tour of Machine LearningBrief Tour of Machine Learning
Brief Tour of Machine Learningbutest
 
Methodological Study Of Opinion Mining And Sentiment Analysis Techniques
Methodological Study Of Opinion Mining And Sentiment Analysis Techniques  Methodological Study Of Opinion Mining And Sentiment Analysis Techniques
Methodological Study Of Opinion Mining And Sentiment Analysis Techniques
ijsc
 
Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)
Julien SIMON
 
An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)
Julien SIMON
 
A scenario based approach for dealing with
A scenario based approach for dealing withA scenario based approach for dealing with
A scenario based approach for dealing with
ijcsa
 
Novi sad ai event 1-2018
Novi sad ai event 1-2018Novi sad ai event 1-2018
Novi sad ai event 1-2018
Jovan Stojanovic
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
Amr Rashed
 
Cost-effective Interactive Attention Learning with Neural Attention Process
Cost-effective Interactive Attention Learning with Neural Attention ProcessCost-effective Interactive Attention Learning with Neural Attention Process
Cost-effective Interactive Attention Learning with Neural Attention Process
MLAI2
 
The Tower of Knowledge A Generic System Architecture
The Tower of Knowledge A Generic System ArchitectureThe Tower of Knowledge A Generic System Architecture
The Tower of Knowledge A Generic System Architecture
Distinguished Lecturer Series - Leon The Mathematician
 
A Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionA Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware Detection
IJCSIS Research Publications
 
Discover How Scientific Data is Used for the Public Good with Natural Languag...
Discover How Scientific Data is Used for the Public Good with Natural Languag...Discover How Scientific Data is Used for the Public Good with Natural Languag...
Discover How Scientific Data is Used for the Public Good with Natural Languag...
BaoTramDuong2
 
Facial Emotion Recognition using Convolution Neural Network
Facial Emotion Recognition using Convolution Neural NetworkFacial Emotion Recognition using Convolution Neural Network
Facial Emotion Recognition using Convolution Neural Network
YogeshIJTSRD
 
Generating domain specific sentiment lexicons using the Web Directory
Generating domain specific sentiment lexicons using the Web Directory Generating domain specific sentiment lexicons using the Web Directory
Generating domain specific sentiment lexicons using the Web Directory
acijjournal
 
Emotion Recognition through Speech Analysis using various Deep Learning Algor...
Emotion Recognition through Speech Analysis using various Deep Learning Algor...Emotion Recognition through Speech Analysis using various Deep Learning Algor...
Emotion Recognition through Speech Analysis using various Deep Learning Algor...
IRJET Journal
 

Similar to A Fuzzy Approach For Multi-Domain Sentiment Analysis (20)

Deep learning tutorial 9/2019
Deep learning tutorial 9/2019Deep learning tutorial 9/2019
Deep learning tutorial 9/2019
 
Deep Learning Tutorial
Deep Learning TutorialDeep Learning Tutorial
Deep Learning Tutorial
 
soft computing BTU MCA 3rd SEM unit 1 .pptx
soft computing BTU MCA 3rd SEM unit 1 .pptxsoft computing BTU MCA 3rd SEM unit 1 .pptx
soft computing BTU MCA 3rd SEM unit 1 .pptx
 
Methodological study of opinion mining and sentiment analysis techniques
Methodological study of opinion mining and sentiment analysis techniquesMethodological study of opinion mining and sentiment analysis techniques
Methodological study of opinion mining and sentiment analysis techniques
 
LearningAG.ppt
LearningAG.pptLearningAG.ppt
LearningAG.ppt
 
Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Big Data Intelligence: from Correlation Discovery to Causal Reasoning Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Big Data Intelligence: from Correlation Discovery to Causal Reasoning
 
Brief Tour of Machine Learning
Brief Tour of Machine LearningBrief Tour of Machine Learning
Brief Tour of Machine Learning
 
Methodological Study Of Opinion Mining And Sentiment Analysis Techniques
Methodological Study Of Opinion Mining And Sentiment Analysis Techniques  Methodological Study Of Opinion Mining And Sentiment Analysis Techniques
Methodological Study Of Opinion Mining And Sentiment Analysis Techniques
 
Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)
 
An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)An Introduction to Deep Learning (May 2018)
An Introduction to Deep Learning (May 2018)
 
A scenario based approach for dealing with
A scenario based approach for dealing withA scenario based approach for dealing with
A scenario based approach for dealing with
 
Novi sad ai event 1-2018
Novi sad ai event 1-2018Novi sad ai event 1-2018
Novi sad ai event 1-2018
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Cost-effective Interactive Attention Learning with Neural Attention Process
Cost-effective Interactive Attention Learning with Neural Attention ProcessCost-effective Interactive Attention Learning with Neural Attention Process
Cost-effective Interactive Attention Learning with Neural Attention Process
 
The Tower of Knowledge A Generic System Architecture
The Tower of Knowledge A Generic System ArchitectureThe Tower of Knowledge A Generic System Architecture
The Tower of Knowledge A Generic System Architecture
 
A Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionA Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware Detection
 
Discover How Scientific Data is Used for the Public Good with Natural Languag...
Discover How Scientific Data is Used for the Public Good with Natural Languag...Discover How Scientific Data is Used for the Public Good with Natural Languag...
Discover How Scientific Data is Used for the Public Good with Natural Languag...
 
Facial Emotion Recognition using Convolution Neural Network
Facial Emotion Recognition using Convolution Neural NetworkFacial Emotion Recognition using Convolution Neural Network
Facial Emotion Recognition using Convolution Neural Network
 
Generating domain specific sentiment lexicons using the Web Directory
Generating domain specific sentiment lexicons using the Web Directory Generating domain specific sentiment lexicons using the Web Directory
Generating domain specific sentiment lexicons using the Web Directory
 
Emotion Recognition through Speech Analysis using various Deep Learning Algor...
Emotion Recognition through Speech Analysis using various Deep Learning Algor...Emotion Recognition through Speech Analysis using various Deep Learning Algor...
Emotion Recognition through Speech Analysis using various Deep Learning Algor...
 

More from Mauro Dragoni

Keynote given at ISWC 2019 Semantic Management for Healthcare Workshop
Keynote given at ISWC 2019 Semantic Management for Healthcare WorkshopKeynote given at ISWC 2019 Semantic Management for Healthcare Workshop
Keynote given at ISWC 2019 Semantic Management for Healthcare Workshop
Mauro Dragoni
 
Translating Ontologies in Real-World Settings
Translating Ontologies in Real-World SettingsTranslating Ontologies in Real-World Settings
Translating Ontologies in Real-World Settings
Mauro Dragoni
 
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information RetrievalKeystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Mauro Dragoni
 
Exploiting Multilinguality For Creating Mappings Between Thesauri
Exploiting Multilinguality For Creating Mappings Between ThesauriExploiting Multilinguality For Creating Mappings Between Thesauri
Exploiting Multilinguality For Creating Mappings Between Thesauri
Mauro Dragoni
 
Semantic-based Process Analysis
Semantic-based Process AnalysisSemantic-based Process Analysis
Semantic-based Process Analysis
Mauro Dragoni
 
Authoring OWL 2 ontologies with the TEX-OWL syntax
Authoring OWL 2 ontologies with the TEX-OWL syntaxAuthoring OWL 2 ontologies with the TEX-OWL syntax
Authoring OWL 2 ontologies with the TEX-OWL syntax
Mauro Dragoni
 
Using Semantic and Domain-based Information in CLIR Systems
Using Semantic and Domain-based Information in CLIR SystemsUsing Semantic and Domain-based Information in CLIR Systems
Using Semantic and Domain-based Information in CLIR Systems
Mauro Dragoni
 
Multilingual Knowledge Organization Systems Management: Best Practices
Multilingual Knowledge Organization Systems Management: Best PracticesMultilingual Knowledge Organization Systems Management: Best Practices
Multilingual Knowledge Organization Systems Management: Best Practices
Mauro Dragoni
 
Collaborative Modeling of Processes and Ontologies with MoKi
Collaborative Modeling of Processes and Ontologies with MoKiCollaborative Modeling of Processes and Ontologies with MoKi
Collaborative Modeling of Processes and Ontologies with MoKi
Mauro Dragoni
 

More from Mauro Dragoni (9)

Keynote given at ISWC 2019 Semantic Management for Healthcare Workshop
Keynote given at ISWC 2019 Semantic Management for Healthcare WorkshopKeynote given at ISWC 2019 Semantic Management for Healthcare Workshop
Keynote given at ISWC 2019 Semantic Management for Healthcare Workshop
 
Translating Ontologies in Real-World Settings
Translating Ontologies in Real-World SettingsTranslating Ontologies in Real-World Settings
Translating Ontologies in Real-World Settings
 
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information RetrievalKeystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
Keystone Summer School 2015: Mauro Dragoni, Ontologies For Information Retrieval
 
Exploiting Multilinguality For Creating Mappings Between Thesauri
Exploiting Multilinguality For Creating Mappings Between ThesauriExploiting Multilinguality For Creating Mappings Between Thesauri
Exploiting Multilinguality For Creating Mappings Between Thesauri
 
Semantic-based Process Analysis
Semantic-based Process AnalysisSemantic-based Process Analysis
Semantic-based Process Analysis
 
Authoring OWL 2 ontologies with the TEX-OWL syntax
Authoring OWL 2 ontologies with the TEX-OWL syntaxAuthoring OWL 2 ontologies with the TEX-OWL syntax
Authoring OWL 2 ontologies with the TEX-OWL syntax
 
Using Semantic and Domain-based Information in CLIR Systems
Using Semantic and Domain-based Information in CLIR SystemsUsing Semantic and Domain-based Information in CLIR Systems
Using Semantic and Domain-based Information in CLIR Systems
 
Multilingual Knowledge Organization Systems Management: Best Practices
Multilingual Knowledge Organization Systems Management: Best PracticesMultilingual Knowledge Organization Systems Management: Best Practices
Multilingual Knowledge Organization Systems Management: Best Practices
 
Collaborative Modeling of Processes and Ontologies with MoKi
Collaborative Modeling of Processes and Ontologies with MoKiCollaborative Modeling of Processes and Ontologies with MoKi
Collaborative Modeling of Processes and Ontologies with MoKi
 

Recently uploaded

Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
James Anderson
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
Peter Spielvogel
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
SOFTTECHHUB
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
sonjaschweigert1
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
KAMESHS29
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 

Recently uploaded (20)

Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 

A Fuzzy Approach For Multi-Domain Sentiment Analysis

  • 1. A Fuzzy Approach For Multi-Domain Sentiment Analysis Mauro Dragoni Fondazione Bruno Kessler (FBK), Shape and Evolve Living Knowledge Unit (SHELL) https://shell.fbk.eu/index.php/Mauro_Dragoni - dragoni@fbk.eu work done in collaboration with Prof. Andrea G.B. Tettamanzi and Prof. Celia da Costa Pereira INRIA Sophia Antipolis June, 19th 2014
  • 2. Outline 1. Background on Sentiment Analysis and Fuzzy Logic 2. Motivations 3. The Approach 4. Evaluation of the Implemented System
  • 3. Sentiment Analysis - 1  Natural Language Processing task for identifying the opinion given by someone with respect to something.  Opinions may be positive, negative, or neutral.  The value associated with the opinion is called “polarity”.
  • 4. Sentiment Analysis - 2  Basic challenges:  Identification of the polarities for each term in the text.  Deciding how to aggregate the different polarities.  Advanced challenges:  Identification of the entities in each sentence (subjects).  Identification of the features describing each entity.  Adaptation of the sentiment model to different domain.  Manage the uncertainty of each learned information within the single domain
  • 5. Fuzzy Logic  Allows to represent imprecise information.  With respect to classical logic, truth-values of assertions may assume all values in the interval [0, 1]  The main element of the fuzzy logic are Fuzzy Sets Hot temperature. x y
  • 6. Motivations - 1  The same concept may have different polarities in different domains.  The polarity associating a concept to a domain may be uncertain due to the different contexts in which it is used.
  • 7. Motivations - 2  The assignment of a unique polarity value to the entire text leads to imprecise information.  In the same text, different aspects have to be analyzed.  A significant concept extraction capability is required. “I bought a new smartphone: the screen is awesome, even if some colors are not very brilliant, but the battery is too short”
  • 8. The Approach  Creation of the knowledge base.  Concept extraction.  Learning of the preliminary sentiment information.  Propagation of the learned information through the knowledge graph.  Modeling of the fuzzy shapes.
  • 9. Creation of the Knowledge Base  Based on the integration of WordNet with SenticNet  WordNet has been enriched with terms extracted from the Roget’s Thesaurus  The links between WordNet and SenticNet have been built by taking into account the synonyms of each WordNet synset and the synonyms of each SenticNet concept.  In order to avoid ambiguities not all associations have been created.  Example: concept “base” WordNet: 20 senses (for the noun) SenticNet: base (beneath, below, understructure)  WordNet sense 2
  • 10. Concept Extraction - 1  Two samples: 1. Today I went to the mall and bought some desserts and a lot of very nice Christmas gifts. 2. The touchscreen is awesome but the battery is too short.
  • 12. Multi-Domain Fuzzy Propagation - 1  Polarity information is propagated through the knowledge base by using an algorithm implementing the simulated annealing strategy.  The propagation of the values is driven by three parameters: annealing rate, propagation rate, and convergence limit.  The intermediate polarity values measured on each concept at the end of each iteration are stored in order to build the final fuzzy shape associated with each combination concept-domain.  A different model is learned for each domain.
  • 13. Multi-Domain Fuzzy Propagation - 2 Domain Initialization: Information Propagation: Stop Condition:
  • 14. Multi-Domain Fuzzy Propagation - 3  Trade-offs:  high propagation rate  risk of polarity convergence  low convergence limit  risk of polarity convergence  lower propagation rate  incomplete graph  high annealing rate  premature stop of the algorithm  high convergence limit  premature stop of the algorithm
  • 16. Modeling of Fuzzy Shapes - 1 Value computed from the training set. Value obtained after the propagation phase. Support computed based on the variance value.
  • 17. Modeling of Fuzzy Shapes - 2 Type 1 level of uncertainty: the core of the fuzzy trapezoid crosses the neutral polarity Type 2 level of uncertainty: only the support of the fuzzy trapezoid crosses the neutral polarity
  • 18. Evaluation of the System - 1  Evaluation on the Blitzer dataset:  25 domains  ~3000 reviews for each domain in the balanced dataset  75% of instances for the training, 25% for the validation  Three baselines: SVM, Max-Entropy, and Naïve-Bayes  Compared the performance by discarding the different levels of uncertainty  Evaluation on:  Elementary Polarity Computation  Concept Extraction + Polarity Computation
  • 19. Evaluation of the System - 2  How fuzzy polarities are aggregated? x
  • 20. Evaluation of the System - 3
  • 21. Evaluation of the System - 4 Approach Avg. Precision Avg. Recall SVM 0.8068 1.0 Naïve-Bayes 0.8227 1.0 Max-Entropy 0.8225 1.0 MDFSA 0.8617 ~ 1.0 MDFSA (Type 1 Uncertainty excluded) 0.8735 ~ 0.7 MDFSA (Type 1 & 2 Uncertainty excluded) 0.8991 ~ 0.5 Elementary Polarity Computation:
  • 22. Evaluation of the System - 5 Approach Precision Recall F-Measure MDFSA 0.25 0.26 0.25 IBM 0.24 0.14 0.18 UNI-NEGEV 0.12 0.05 0.07 Concept Extraction + Polarity Computation (ESWC 2014 Challenge):
  • 23. Future Work  Integration of more knowledge bases into the system.  Improve how ambiguities are addressed.  Improve the concept extraction module.  Extending the approach for addressing multilingualism.  Apply the approach to the social network environment.

Editor's Notes

  1. Fuzzy logic allows to increase the description ability of the crisp logics, because it allows one to describe facts using values that express imprecise situations; so, we exit from the constraint of using only 0 or 1 values, but we can use all values in this interval. The main element of fuzzy logic is constituted by fuzzy sets that represent the sets of the membership relations between the environment objects and a particular subset of them.