SpringerLink Springer Biomedical and Life Sciences eBooks 2017 English+International

Incluye referencias bibliográficas e índice

Preface; Contents; 1 Affective Computing and Sentiment Analysis; 1.1 Introduction; 1.2 Common Tasks; 1.3 General Categorization; 1.4 Conclusion; References; 2 Many Facets of Sentiment Analysis; 2.1 Definition of Opinion; 2.1.1 Opinion Definition; 2.1.2 Sentiment Target; 2.1.3 Sentiment and Its Intensity; 2.1.4 Opinion Definition Simplified; 2.1.5 Reason and Qualifier for Opinion; 2.1.6 Objective and Tasks of Sentiment Analysis; 2.2 Definition of Opinion Summary; 2.3 Affect, Emotion, and Mood; 2.3.1 Affect, Emotion, and Mood in Psychology; 2.3.2 Affect, Emotion, and Mood in Sentiment Analysis.

2.4 Different Types of Opinions2.4.1 Regular and Comparative Opinions; 2.4.2 Subjective and Fact-Implied Opinions; 2.4.3 First-Person and Non-First-Person Opinions; 2.4.4 Meta-opinions; 2.5 Author and Reader Standpoint; 2.6 Summary; References; 3 Reflections on Sentiment/Opinion Analysis; 3.1 Introduction; 3.2 A Review of Current Sentiment Analysis; 3.3 The Needs and Goals Behind Sentiments; 3.3.1 Maslow's Hierarchy of Needs; 3.3.2 Finding Appropriate Goals for Actions and Entities; 3.4 Toward a Practical Computational Approach; 3.4.1 Examples and Illustration.

3.4.2 A Computational Model of Each Part3.4.3 Prior/Default Knowledge About Opinion Holders; 3.5 Conclusion and Discussion; References; 4 Challenges in Sentiment Analysis; 4.1 Introduction; 4.2 The Array of Sentiment Analysis Tasks; 4.2.1 Sentiment at Different Text Granularities; 4.2.2 Detecting Sentiment of the Writer, Reader, and Other Entities; 4.2.3 Sentiment Towards Aspects of an Entity; 4.2.4 Stance Detection; 4.2.5 Detecting Semantic Roles of Feeling; 4.2.6 Detecting Affect and Emotions; 4.3 Sentiment of Words; 4.3.1 Manually Generated Term-Sentiment Association Lexicons.

4.3.2 Automatically Generated Term-Sentiment Association Lexicons4.4 Sentiment of Phrases, Sentences, and Tweets: Sentiment Composition; 4.4.1 Negated Expressions; 4.4.2 Phrases with Degree Adverbs, Intensifiers, and Modals; 4.4.3 Sentiment of Sentences, Tweets, and SMS messages; 4.4.4 Sentiment in Figurative Expressions; 4.5 Challenges in Annotating for Sentiment; 4.6 Challenges in Multilingual Sentiment Analysis; 4.7 Challenges in Applying Sentiment Analysis; References; 5 Sentiment Resources: Lexicons and Datasets; 5.1 Introduction; 5.2 Labels; 5.2.1 Stand-Alone Labels; 5.2.2 Dimensions.

5.2.3 Structures5.3 Lexicons; 5.3.1 Sentiment Lexicons; 5.3.1.1 SentiWordNet; 5.3.1.2 SO-CAL; 5.3.1.3 Sentiment Treebank & Associated Lexicon; 5.3.1.4 Summary; 5.3.2 Emotion Lexicons; 5.3.2.1 LIWC; 5.3.2.2 ANEW; 5.3.2.3 Emo-Lexicon; 5.3.2.4 WordNet-Affect; 5.3.2.5 Chinese Emotion Lexicon; 5.3.2.6 SenticNet; 5.3.2.7 Summary; 5.4 Sentiment-Annotated Datasets; 5.4.1 Sources of Data; 5.4.2 Obtaining Labels; 5.4.3 Popular Sentiment-Annotated Datasets; 5.5 Bridging the Language Gap; 5.6 Applications of Sentiment Resources; 5.7 Conclusion; References.

This edited work presents studies and discussions that clarify the challenges and opportunities of sentiment analysis research. While sentiment analysis research has become very popular in the past ten years, most companies and researchers still approach it simply as a polarity detection problem. In reality, sentiment analysis is a 'suitcase problem' that requires tackling many natural language processing subtasks, including microtext analysis, sarcasm detection, anaphora resolution, subjectivity detection and aspect extraction. In this book, the authors propose an overview of the main issues and challenges associated with current sentiment analysis research and provide some insights on practical tools and techniques that can be exploited to both advance the state of the art in all sentiment analysis subtasks and explore new areas in the same context. Readers will discover sentiment mining techniques that can be exploited for the creation and automated upkeep of review and opinion aggregation websites, in which opinionated text and videos are continuously gathered from the Web and not restricted to just product reviews, but also to wider topics such as political issues and brand perception. The book also enables researchers to see how affective computing and sentiment analysis have a great potential as a sub-component technology for other systems. They can enhance the capabilities of customer relationship management and recommendation systems allowing, for example, to find out which features customers are particularly happy about or to exclude from the recommendations items that have received very negative feedbacks. Similarly, they can be exploited for affective tutoring and affective entertainment or for troll filtering and spam detection in online social communication.