3 Semantic Analysis of Social Media Texts
3.2.1 Mapping Social Media Information on Maps
3.2.2 Readily Available Geo-location Information
3.2.3 Geo-location based on Network Infrastructure
3.2.4 Geo-location based on the Social Network Structure
3.2.5 Content-based Location Detection
3.2.6 Evaluation Measures for Geo-location Detection
3.3 Entity Linking and Disambiguation
3.3.1 Detecting Entities and Linked Data
3.3.2 Evaluation Measures for Entity Linking
3.4 Opinion Mining and Emotion Analysis
3.4.1 Sentiment Analysis
3.4.2 Emotion Analysis
3.4.3 Sarcasm Detection
3.4.4 Evaluation Measures for Opinion and Emotion Classification
3.5 Event and Topic Detection
3.5.1 Specified vs. Unspecified Event Detection
3.5.2 New vs. Retrospective Events
3.5.3 Emergency Situation Awareness
3.5.4 Evaluation Measures for Event Detection
3.6 Automatic Summarization
3.6.1 Update Summarization
3.6.2 Network Activity Summarization
3.6.3 Event Summarization
3.6.4 Opinion Summarization
3.6.5 Evaluation Measures for Summarization
3.7 Machine Translation
3.7.1 Adapting Phrase-based Machine Translation to Normalize Medical Terms
3.7.2 Translating Government Agencies’ Tweet Feeds
3.7.3 Hashtag Occurrence, Layout, and Translation
3.7.4 Machine Translation for Arabic Social Media
3.7.5 Evaluation Measures for Machine Translation
3.8 Summary
4 Applications of Social Media Text Analysis
4.1 Introduction
4.2 Healthcare Applications
4.3 Financial Applications
4.4 Predicting Voting Intentions
4.5 Media Monitoring
4.6 Security and Defense Applications
4.7 Disaster Response Applications
4.8 NLP-based User Modeling
4.9 Applications for Entertainment
4.10 NLP-based Information Visualization for Social Media
4.11 Government Communication
4.12 Summary
5 Data Collection, Annotation, and Evaluation
5.1 Introduction
5.2 Discussion on Data Collection and Annotation
5.3 Spam and Noise Detection
5.4 Privacy and Democracy in Social Media
5.5 Evaluation Benchmarks
5.6 Summary
6.1 Conclusion
6.2 Perspectives
A TRANSLI: a Case Study for Social Media Analytics and Monitoring
A.1 TRANSLI architecture
A.2 User Interface
Preface to the Second Edition
This book presents the state-of-the-art in research and empirical studies in the field of Natural Language Processing (NLP) for the semantic analysis of social media data. Because the field is continuously growing, this second edition adds information about recently proposed methods and their results for the tasks and applications that we covered in the first edition.
Over the past few years, online social networking sites have revolutionized the way we communicate with individuals, groups, and communities, and altered everyday practices. The unprecedented volume and variety of user-generated content and the user interaction network constitute new opportunities for understanding social behavior and building socially intelligent systems.
Much of the research on social networks and the mining of the social web is based on graph theory. That is apt because a social structure is made up of a set of social actors and a set of the dyadic ties between these actors. We believe that the graph mining methods for structure and information diffusion or influence spread in social networks need to be combined with the content analysis of social media. This provides the opportunity for new applications that use the information publicly available as a result of social interactions. Adapted classic NLP methods can partially solve the problem of social media content analysis focusing on the posted messages. When we receive a text of less than 10 characters, including an emoticon and a heart, we understand it and even respond to it! It is impossible to use NLP methods to process this type of document, but there is a logical message in social media data based on which two people can communicate. The same logic dominates worldwide, and people from all over the world use it to share and communicate with each other. There is a new and challenging language for NLP.
We believe that we need new theories and algorithms for semantic analysis of social media data, as well as a new way of approaching the big data processing. By semantic analysis, in this book, we mean the linguistic processing of the social media messages enhanced with semantics, and possibly also