Multimodal Sentiment Analysis

Softcover Nachdruck of the original 1. Auflage 2018
ISBN: 978-3-030-06956-8
Verlag: Springer International Publishing

Buch, Englisch, Band 8, 214 Seiten, Previously published in hardcover, Format (B × H): 155 mm x 235 mm, Gewicht: 401 g

Reihe: Socio-Affective Computing

This latest volume in the series, Socio-Affective Computing, presents a set of novel approaches to analyze opinionated videos and to extract sentiments and emotions. 

Textual sentiment analysis framework as discussed in this book contains a novel way of doing sentiment analysis by merging linguistics with machine learning. Fusing textual information with audio and visual cues is found to be extremely useful which improves text, audio and visual based unimodal sentiment analyzer.

This volume covers the three main topics of: textual preprocessing and sentiment analysis methods; frameworks to process audio and visual data; and methods of textual, audio and visual features fusion.

The inclusion of key visualization and case studies will enable readers to understand better these approaches. 

Aimed at the Natural Language Processing, Affective Computing and Artificial Intelligence audiences, this comprehensive volume will appeal to a wide readership and will help readers to understand key details on multimodal sentiment analysis.

Zielgruppe

Research

Autoren/Hrsg.

Poria, Soujanya

Cambria, Erik

Hussain, Amir

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Natürliche Sprachen & Maschinelle Übersetzung
• Interdisziplinäres Wissenschaften Wissenschaften Interdisziplinär Neurowissenschaften, Kognitionswissenschaft
• Geisteswissenschaften Sprachwissenschaft Übersetzungswissenschaft, Translatologie, Dolmetschen
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Computer Vision
• Mathematik | Informatik EDV | Informatik Professionelle Anwendung

Inhaltsverzeichnis

Preface 

1 Introduction and Motivation
Research Challenges in Text-Based Sentiment Analysis
Research Challenges in Multimodal Sentiment Analysis
Overview of the Proposed Framework
Contributions of this Book
Book Organisation

 2 BackgroundAffective Computing
Sentiment Analysis
Pattern Recognition  
Feature Selection
Model Evaluation Techniques  
Model Validation Techniques
Classification Techniques
Feature-Based Text Representation
Conclusion

 3 Literature Survey and DatasetsIntroduction
Available Datasets
Visual, Audio Features for Affect Recognition
Multimodal Affect Recognition
Available APIs
Discussion
Conclusion

 4 Concept Extraction from Natural Text for Concept Level Text AnalysisIntroduction
The patterns for concept extraction
Experiments and Results
Conclusion

 5 EmoSenticSpace: Dense concept-based affective features with common-sense knowledgeIntroduction
Lexical Resources Used
Features Used for Classification
Fuzzy Clustering
Hard Clustering
Implementation
Direct Evaluation Of The Assigned Emotion Labels
Construction Of Emosenticspace
Performance on Applications
Summary of Lexical Resources and Features Used
Conclusion

 6 Sentic Patterns: Sentiment Data Flow Analysis by Means of Dynamic Linguistic PatternsIntroduction
General rules
Combining sentic patterns with machine learning for text-based
sentiment analysis
Evaluation
Conclusion 

7 Combining Textual Clues with Audio-Visual Information for Multimodal Sentiment AnalysisIntroduction
Extracting Features from Textual Data
Extracting Features from Visual Data
Extracting Features from Audio Data
Experimental Results
Speeding up the computational time: The role of ELM
Improved multimodal sentiment analysis: Deep learning-based
visual feature extraction
Convolutional Recurrent Multiple Kernel Learning (CRMKL)
Experimental Results and Discussion
Conclusion 

8 Conclusion and Future Work
Social Impact
Advantages
Limitations
Future Work

Index