Opinion Analysis in Interactions

Book description

As time goes on, big companies such as Amazon, Microsoft, Google and Apple become increasingly interested in virtual assistants. The interest and development of social robots has put research into affective and social computing at the forefront of the scene.

The aim of Opinion Analysis in Interactions is to present methods based on artificial intelligence through a combination of machine learning models and symbolic approaches. Also discussed are natural language processing and affective computing, via the analysis and generation of socio-emotional signals.

The book explores the analysis of opinions in human–human interaction and tackles the less-explored (yet crucial) challenges related to the analysis methods of user opinions within the context of human–agent interaction. It also illustrates the implementation of strategies for selecting and generating agent utterances in response to user opinions, and opens up perspectives on the agent’s multimodal generation of utterances that hold attitudes.

Table of contents

  1. Cover
  2. Preface
  3. Introduction: From Opinion Mining to Human–agent Interactions
    1. I.1. Terminologies and theoretical models of opinions
    2. I.2. Computational models of opinions
    3. I.3. Human–agent interactions and socio-emotional behaviors
    4. I.4. Outline of the book
  4. 1 Oral and Written Interaction Corpora
    1. 1.1. Oral H–H corpora: call centers and satisfaction surveys
    2. 1.2. Written H–H corpora: forums
    3. 1.3. Oral H–A corpora: virtual assistants and robots
    4. 1.4. Written H–A corpus: chatbot
    5. 1.5. Comparative study of different corpora
    6. 1.6. Conclusion
  5. 2 Analyzing User Opinions in Human–human Interactions
    1. 2.1. From linguistic modeling to machine learning
    2. 2.2. Learning to account for linguistic specificities
    3. 2.3. Conclusion
  6. 3 Analyzing User Opinions in Human–Agent Interactions
    1. 3.1. Choice of phenomena to study in relation to applications
    2. 3.2. Rule-based system to take into account interaction
    3. 3.3. Hybrid approach for taking account of interactions
    4. 3.4. Evaluation for human–agent interactions
    5. 3.5. Conclusion
  7. 4 Socio-emotional Interaction Strategies: the Case of Alignment
    1. 4.1. Theoretical models
    2. 4.2. Qualitative and quantitative corpus analysis
    3. 4.3. Computational model of verbal alignment
    4. 4.4. Method for evaluating an alignment module
    5. 4.5. Conclusion
  8. 5 Generating Socio-emotional Behaviors
    1. 5.1. Generating agent prosody
    2. 5.2. Intonation, facial expressions and sequence mining
    3. 5.3. Generation of coverbal gestures for agents
    4. 5.4. Conclusion
  9. Conclusion: Summary and Directions for Future Research
  10. References
  11. Index
  12. End User License Agreement

Product information

  • Title: Opinion Analysis in Interactions
  • Author(s): Chloe Clavel
  • Release date: September 2019
  • Publisher(s): Wiley-ISTE
  • ISBN: 9781786304193