Sentiment Analysis in Social Networks

ISBN-13: 9780128044124 / Angielski / Miękka / 2016 / 284 str.

Federico Pozzi; Elisabetta Fersini; Enza Messina

Opis

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

Spis treści

Chapter 1: Challenges of Sentiment Analysis in Social Networks: An Overview

Chapter 2: Beyond Sentiment: How Social Network Analytics Can Enhance Opinion Mining and Sentiment Analysis

Chapter 3: Semantic Aspects in Sentiment Analysis

Chapter 4: Linked Data Models for Sentiment and Emotion Analysis in Social Networks

Chapter 5: Sentic Computing for Social Network Analysis

Chapter 6: Sentiment Analysis in Social Networks: A Machine Learning Perspective

Chapter 7: Irony, Sarcasm, and Sentiment Analysis

Chapter 8: Suggestion Mining From Opinionated Text

Chapter 9: Opinion Spam Detection in Social Networks

Chapter 10: Opinion Leader Detection

Chapter 11: Opinion Summarization and Visualization

Chapter 12: Sentiment Analysis With SpagoBI

Chapter 13: SOMA: The Smart Social Customer Relationship Management Tool: Handling Semantic Variability of Emotion Analysis With Hybrid Technologies

Chapter 14: The Human Advantage: Leveraging the Power of Predictive Analytics to Strategically Optimize Social Campaigns

Chapter 15: Price-Sensitive Ripples and Chain Reactions: Tracking the Impact of Corporate Announcements With Real-Time Multidimensional Opinion Streaming

Chapter 16: Conclusion and Future Directions

O autorze

Dr. Federico Alberto Pozzi received the Ph.D. in Computer Science at the University of Milano - Bicocca (Italy). His Ph.D. thesis is focused on Probabilistic Relational Models for Sentiment Analysis in Social Networks. His research interests primarily focus on Data Mining, Text Mining, Machine Learning, Natural Language Processing and Social Network Analysis, in particular applied to Sentiment Analysis and Community Discovery in Social Networks. He currently works at SAS Institute (Italy) as Senior Solutions Specialist - Integrated Marketing Management & Analytics. Dr. Elisabetta Fersini is currently a postdoctoral research fellow at the University of Milano - Bicocca (Italy). Her research activity is mainly focused on statistical relational learning with particular interests in supervised and unsupervised classification. The research activity finds application to Web/Text mining, Sentiment Analysis, Social Network Analysis, e-Justice and Bioinformatics. She actively participated to several national and international research projects. She has been an evaluator for international research projects and member of different scientific committees. She co-founded an academic spin-off specialized in sentiment analysis and community discovery in social networks. Prof. Enza Messina is a Professor in Operations Research at the Department of Informatics Systems and Communications, University of Milano-Bicocca, where she leads the research Laboratory MIND (Models in decision making and data analysis). She holds a Ph.D. in Computational Mathematics and Operations Research from the University of Milano. Her research activity is mainly focused on decision models under uncertainty and more recently on statistical relational models for data analysis and knowledge extraction. In particular, she developed relational classi?cation and clustering models that finds applications in different domains such as systems biology, e-justice, text mining and social network analysis. Prof. Bing Liu is a professor of computer science at the University of Illinois at Chicago. He received his PhD in Arti?cial Intelligence from the University of Edinburgh. His current research interests include sentiment analysis and opinion mining, data mining, machine learning, and natural language processing. He has published extensively in top conferences and journals, and is the author of three books: Sentiment Analysis and Opinion Mining (2012), Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data (first edition, 2007; second edition, 2011), and Sentiment Analysis: Mining Opinions, Sentiments and Emotions (2015). Two of his papers received 10-year test-of-time awards from KDD, the premier conference of data mining and big data. His research has also been cited on the front page of the New York Times. He currently serves as the Chair of ACM SIGKDD, and is an Fellow of ACM, AAAI, and IEEE.