Mode of access: World Wide Web.

System requirements: Adobe Acrobat Reader.

Part of: Synthesis digital library of engineering and computer science.

Series from website.

Includes bibliographical references (p. 135-165).

1. Sentiment analysis: a fascinating problem -- 1.1 Sentiment analysis applications -- 1.2 Sentiment analysis research -- 1.2.1 Different levels of analysis -- 1.2.2 Sentiment lexicon and its issues -- 1.2.3 Natural language processing issues -- 1.3 Opinion spam detection -- 1.4 What's ahead --

2. The problem of sentiment analysis -- 2.1 Problem definitions -- 2.1.1 Opinion definition -- 2.1.2 Sentiment analysis tasks -- 2.2 Opinion summarization -- 2.3 Different types of opinions -- 2.3.1 Regular and comparative opinions -- 2.3.2 Explicit and implicit opinions -- 2.4 Subjectivity and emotion -- 2.5 Author and reader standpoint -- 2.6 Summary --

3. Document sentiment classification -- 3.1 Sentiment classification using supervised learning -- 3.2 Sentiment classification using unsupervised learning -- 3.3 Sentiment rating prediction -- 3.4 Cross-domain sentiment classification -- 3.5 Cross-language sentiment classification -- 3.6 Summary --

4. Sentence subjectivity and sentiment classification -- 4.1 Subjectivity classification -- 4.2 Sentence sentiment classification -- 4.3 Dealing with conditional sentences -- 4.4 Dealing with sarcastic sentences -- 4.5 Cross-language subjectivity and sentiment classification -- 4.6 Using discourse information for sentiment classification -- 4.7 Summary --

5. Aspect-based sentiment analysis -- 5.1 Aspect sentiment classification -- 5.2 Basic rules of opinions and compositional semantics -- 5.3 Aspect extraction -- 5.3.1 Finding frequent nouns and noun phrases -- 5.3.2 Using opinion and target relations -- 5.3.3 Using supervised learning -- 5.3.4 Using topic models -- 5.3.5 Mapping implicit aspects -- 5.4 Identifying resource usage aspect -- 5.5 Simultaneous opinion lexicon expansion and aspect extraction -- 5.6 Grouping aspects into categories -- 5.7 Entity, opinion holder, and time extraction -- 5.8 Coreference resolution and word sense disambiguation -- 5.9 Summary --

6. Sentiment lexicon generation -- 6.1 Dictionary-based approach -- 6.2 Corpus-based approach -- 6.3 Desirable and undesirable facts -- 6.4 Summary --

7. Opinion summarization -- 7.1 Aspect-based opinion summarization -- 7.2 Improvements to aspect-based opinion summarization -- 7.3 Contrastive view summarization -- 7.4 Traditional summarization -- 7.5 Summary --

8. Analysis of comparative opinions -- 8.1 Problem definitions -- 8.2 Identify comparative sentences -- 8.3 Identifying preferred entities -- 8.4 Summary --

9. Opinion search and retrieval -- 9.1 Web search vs. opinion search -- 9.2 Existing opinion retrieval techniques -- 9.3 Summary --

10. Opinion spam detection -- 10.1 Types of spam and spamming -- 10.1.1 Harmful fake reviews -- 10.1.2 Individual and group spamming -- 10.1.3 Types of data, features, and detection -- 10.2 Supervised spam detection -- 10.3 Unsupervised spam detection -- 10.3.1 Spam detection based on atypical behaviors -- 10.3.2 Spam detection using review graph -- 10.4 Group spam detection -- 10.5 Summary --

11. Quality of reviews -- 11.1 Quality as regression problem -- 11.2 Other methods -- 11.3 Summary --

12. Concluding remarks -- Bibliography -- Author biography.

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

INSPEC

Google scholar

Google book search

Sentiment analysis and opinion mining is the field of study that analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, Web mining, and text mining. In fact, this research has spread outside of computer science to the management sciences and social sciences due to its importance to business and society as a whole. The growing importance of sentiment analysis coincides with the growth of social media such as reviews, forum discussions, blogs, micro-blogs, Twitter, and social networks. For the first time in human history, we now have a huge volume of opinionated data recorded in digital form for analysis.

Also available in print.

Title from PDF t.p. (viewed on June 13, 2012).