UID:
edoccha_9958236226702883
Umfang:
1 online resource (286 pages) :
,
illustrations, tables
Ausgabe:
1st edition
ISBN:
0-12-804412-8
Inhalt:
The aim of Sentiment Analysis is to define automatic tools able to extract subjective information from texts in natural language, such as opinions and sentiments, in order to create structured and actionable knowledge to be used by either a decision support system or a decision maker. Sentiment analysis has gained even more value with the advent and growth of social networking. Sentiment Analysis in Social Networks begins with an overview of the latest research trends in the field. It then discusses the sociological and psychological processes underling social network interactions. The book explores both semantic and machine learning models and methods that address context-dependent and dynamic text in online social networks, showing how social network streams pose numerous challenges due to their large-scale, short, noisy, context- dependent and dynamic nature. Further, this volume: Takes an interdisciplinary approach from a number of computing domains, including natural language processing, machine learning, big data, and statistical methodologies Provides insights into opinion spamming, reasoning, and social network analysis Shows how to apply sentiment analysis tools for a particular application and domain, and how to get the best results for understanding the consequences Serves as a one-stop reference for the state-of-the-art in social media analytics Takes an interdisciplinary approach from a number of computing domains, including natural language processing, big data, and statistical methodologies Provides insights into opinion spamming, reasoning, and social network mining Shows how to apply opinion mining tools for a particular application and domain, and how to get the best results for understanding the consequences Serves as a one-stop reference for the state-of-the-art in social media analytics
Anmerkung:
Front Cover -- Sentiment Analysis in Social Networks -- Copyright -- Contents -- Contributors -- Editors' Biographies -- Preface -- Acknowledgments -- Chapter 1: Challenges of Sentiment Analysis in Social Networks: An Overview -- 1. Background -- 2. Sentiment Analysis in Social Networks: A New Research Approach -- 3. Sentiment Analysis Characteristics -- 3.1. Sentiment Categorization: Objective Versus Subjective Sentences -- 3.2. Levels of Analysis -- 3.3. Regular Versus Comparative Opinion -- 3.4. Explicit Versus Implicit Opinions -- 3.5. The Role of Semantics -- 3.6. Dealing With Figures of Speech -- 3.7. Relationships in Social Networks -- 4. Applications -- References -- Chapter 2: Beyond Sentiment: How Social Network Analytics Can Enhance Opinion Mining and Sentiment Analysis -- 1. Introduction -- 2. Definitions and History of Online Social Networks -- 2.1. What Exactly Is an Online Social Network? -- 2.2. Brief History of Online Social Networks -- 3. Are Online Social Networks All the Same? Features and Metrics -- 3.1. Types of User-Generated Content -- 3.2. Types of Relationships Between Users -- 3.3. Indexes and Metrics to Analyze Data Collected Through Online Social Networks -- 4. Psychological and Motivational Factors for People to Share Opinions and to Express Themselves on Social Networks -- 4.1. Need to Belong -- 4.2. Need for Cognition -- 4.3. Self-Presentation and Impression Management -- 5. From Sociology Principles to Social Networks Analytics -- 5.1. Tie Strengths -- Homophily or Similarity Breeds Connection -- 5.3. Source Credibility -- 6. How Can Social Network Analytics Improve Sentiment Analysis on Online Social Networks? -- 6.1. What Is Social Network Analysis? -- 6.2. How to Integrate Social Network Analytics in Sentiment Analysis: Some Examples -- 7. Conclusion and Future Directions -- References.
,
Chapter 3: Semantic Aspects in Sentiment Analysis -- 1. Introduction -- 2. Semantic Resources for Sentiment Analysis -- 2.1. Classical Resources on Sentiment -- 2.2. Beyond the Polarity Valence: Emotion Lexica, Ontologies,and Psycholinguistic Resources -- 2.2.1. Emotion lexica: finer-grained affective lexica based on emotional categories -- 2.2.2. Psycholinguistic resources and other accounts of affect -- 2.2.3. Concept-based resources and ontologies: toward a knowledge-based approach to sentiment analysis -- 2.3. Social Media Corpora Annotated for Sentiment and Fine Emotion Categories -- 3. Using Semantics in Sentiment Analysis -- 3.1. Lexical Information -- 3.2. Distributional Semantics -- 3.3. Entities, Properties, and Relations -- 3.4. Concept-Level Sentiment Analysis: Reasoning With Semantics -- Conclusions -- References -- Chapter 4: Linked Data Models for Sentiment and Emotion Analysis in Social Networks -- 1. Introduction -- 2. Marl: A Vocabulary for Sentiment Annotation -- 3. Onyx: A Vocabulary for Emotion Annotation -- 3.1. Onyx Extensibility: Vocabularies -- 3.2. Emotion Markup Language -- 4. Linked Data Corpus Creation for Sentiment Analysis -- 4.1. Sentiment Corpus -- 4.2. Emotion Corpus -- 5. Linked Data Lexicon Creation for Sentiment Analysis -- 5.1. Sentiment Lexicon -- 5.2. Emotion Lexicon -- 6. Sentiment and Emotion Analysis Services -- 7. Case Study: Generation of a Domain-Specific Sentiment Lexicon -- Conclusions -- Acknowledgments -- References -- Chapter 5: Sentic Computing for Social Network Analysis -- 1. Introduction -- 2. Related Work -- 3. Affective Characterization -- 4. Applications -- 4.1. Troll Filtering -- 4.2. Social Media Marketing -- 4.3. A Model for Sentiment Classification in Twitter -- 5. Future Trends and Directions -- 6. Conclusion -- References.
,
Chapter 6: Sentiment Analysis in Social Networks: A Machine Learning Perspective -- 1. Introduction -- 2. Polarity Classification in Online Social Networks: The Key Elements -- 3. Polarity Classification: Natural Language and Relationships -- 3.1. Leveraging Natural Language -- 3.1.1. Supervised learning -- 3.1.2. Semisupervised learning -- 3.1.3. Unsupervised models -- 3.2. Leveraging Natural Language and Relationships -- 3.3.1. Supervised learning -- 3.2.2. Semisupervised learning -- 3.2.3. Unsupervised learning -- 4. Applications -- 5. Future Directions -- 6. Conclusion -- References -- Chapter 7: Irony, Sarcasm, and Sentiment Analysis -- 1. Introduction -- 2. Irony and Sarcasm Detection -- 2.1. Irony Detection -- 2.2. Sarcasm Detection -- 3. Figurative Language and Sentiment Analysis -- 3.1. Sentiment Polarity Classification at Evalita 2014 -- 3.2. Sentiment Analysis in Twitter at SemEval 2014 and 2015 -- 3.3. Sentiment Analysis of Figurative Language in Twitter at SemEval 2015 -- 4. Future Trends and Directions -- 5. Conclusions -- Acknowledgments -- References -- Chapter 8: Suggestion Mining From Opinionated Text -- 1. Introduction -- 2. Sentiments and Suggestions -- 3. Task Definition and Typology of Suggestions -- 4. Datasets -- 5. Approaches for Suggestion Detection -- 5.1. Linguistic Observations in Suggestions -- 5.2. Detection of Suggestions for Improvements -- 5.3. Detection of Suggestions to Fellow Customers -- 6. Applications -- 7. Future Trends and Directions -- 8. Summary -- Acknowledgments -- References -- Chapter 9: Opinion Spam Detection in Social Networks -- 1. Introduction -- 2. Related Work -- 3. Review Spammer Detection Leveraging Reviewing Burstiness -- 3.1. Burst Detection -- 3.2. Spammer Detection Under Review Bursts -- 3.2.1. Reviewer modeling using Markov random fields -- Node prior potentials.
,
Edge compatibility potentials -- 3.2.2. Reviewer identity inference using loopy belief propagation -- 4. Detecting Campaign Promoters on Twitter -- 4.1. Campaign Promoter Modeling Using Typed Markov Random Fields -- 4.1.1. Node prior potentials -- 4.1.2. Compatibility potentials -- 4.2. Inference -- 4.3. Opinion Spam Evaluation -- 5. Spotting Spammers Using Collective Positive-Unlabeled Learning -- 5.1. Problem Definition -- 5.2. Collective Classification -- 5.3. Model Evaluation -- 5.4. Trends and Directions -- 6. Conclusion -- Acknowledgments -- References -- Chapter 10: Opinion Leader Detection -- 1. Introduction -- 2. Problem Definition -- 3. Approaches -- 3.1. Measures Based on Network Structure -- 3.1.1. Centrality measures -- 3.1.2. Community-driven measures -- 3.1.3. Summary -- 3.2. Methods Based on Interaction -- 3.3. Methods Based on Content Mining -- 3.4. Methods Based on Content and Interaction -- 4. Discussion -- 5. Conclusions -- References -- Chapter 11: Opinion Summarization and Visualization -- 1. Introduction -- 2. Opinion Summarization -- 2.1. Challenges -- 2.1.1. Challenges of summarizing noisy text -- 2.2.1. Challenges of summarizing opinion-filled text -- 2.2. Evaluation -- 2.2.1. Intrinsic evaluation -- 2.2.2. Extrinsic evaluation -- 2.3. Opinion Summarization Approaches -- 3. Opinion Visualization -- 3.1. Challenges for Opinion Visualization -- 3.2. Text Genres and Tasks for Opinion Visualization -- 3.2.1. Customer feedback -- 3.2.2. User reactions to large-scale events -- 3.2.3. Online conversations -- 3.3. Opinion Visualization of Customer Feedback -- 3.3.1. Explore opinions on a single entity -- 3.3.2. Compare opinions for multiple entities -- 3.4. Opinion Visualization of User Reactions to Large-Scale Events via Microblogs -- 3.5. Visualizing Opinions in Online Conversations.
,
3.6. Current and Future Trends in Opinion Visualization -- 3.6.1. Visualizing uncertainty in opinions -- 3.6.2. Scaling up for big data -- 4. Conclusion -- References -- Chapter 12: Sentiment Analysis With SpagoBI -- 1. Introduction to SpagoBI -- 2. Social Network Analysis With SpagoBI -- 2.1. Main Purpose -- 2.2. Features -- 2.3. Use Case -- 3. Algorithms Used -- 4. Conclusion -- Chapter 13: SOMA: The Smart Social Customer Relationship Management Tool: Handling Semantic Variability of Emotion ... -- 1. Introduction -- 2. Definition of Sentiment and Emotion Mining -- 3. Previous Work -- 4. A Silver Standard Corpus for Emotion Classification in Tweets -- 5. General System -- 5.1. Hybrid Operable Platform for Language Managementand Extensible Semantics -- 5.2. The Machine Learning Approach -- 5.3. The Symbolic Approach -- 6. Results and Evaluation -- 6.1. Tweet Emotion Detection -- 6.2. Tweet Relevance -- 7. Conclusion -- Acknowledgments -- References -- Chapter 14: The Human Advantage: Leveraging the Power of Predictive Analytics to Strategically Optimize Social Campaigns* -- 1. Introduction -- 2. The Current Philosophy Around Sentiment Analysis -- 3. KRC Research's Digital Content and Sentiment Philosophy -- 3.1. Pretesting Is Crucial -- 3.2. Continuously Learn How to Improve -- 3.3. Use Scientific Sampling Rather Than Reviewing Every Pieceof Content -- 3.4. Build Predictive Models -- 4. KRC Research's Sentiment and Analytics Approach -- 5. Case Study -- 5.1. Life Insurance Organization -- 6. Conclusion -- Chapter 15: Price-Sensitive Ripples and Chain Reactions: Tracking the Impact of Corporate Announcements With Real-Time ... -- 1. Introduction -- 2. Architecture -- 2.1. Data Sources and Filters -- 2.2. Core Natural Language Processing and Opinion Metrics -- 2.3. Opinion Metrics -- 2.4. Indexing -- 2.5. Real-Time Opinion Streaming.
,
3. Multidimensional Opinion Metrics.
Weitere Ausg.:
ISBN 0-12-804438-1
Sprache:
Englisch
Bookmarklink
