Sentic Computing Techniques, Tools, and Applications [Paperback]

In this book common sense computing techniques are further developed and applied to bridge the semantic gap between word-level natural language data and the concept-level opinions conveyed by these. In particular, the ensemble application of graph mining and multi-dimensionality reduction techniques is exploited on two common sense knowledge bases to develop a novel intelligent engine for open-domain opinion mining and sentiment analysis. The proposed approach, termed sentic computing, performs a clause-level semantic analysis of text, which allows the inference of both the conceptual and emotional information associated with natural language opinions and, hence, a more efficient passage from (unstructured) textual information to (structured) machine-processable data.

Introduction

1.1 Sentic Computing
? 1.1.1 Motivations
? 1.1.2 Aims
? 1.1.3 Methodology

Background

2.1 Opinion Mining and Sentiment Analysis
? 2.1.1 The Buzz Mechanism
? 2.1.2 Origins and Peculiarities
? 2.1.3 Sub-Tasks
2.2 Main Approaches to Opinion Mining
? 2.2.1 From Heuristics to Discourse Structure
? 2.2.2 From Coarse to Fine Grained
? 2.2.3 From Keywords to Concepts
2.3 Towards Machines with Common Sense
? 2.3.1 The Importance of Common Sense
? 2.3.2 Knowledge Representation
? 2.3.3 From Logical Inference to Digital Intuition
2.4 Conclusions

Techniques

3.1 Affective Blending: Enabling Emotion-Sensitive Inference
? 3.1.1 AffectNet
? 3.1.2 AffectiveSpace
3.2 Affective Categorisation: Modelling Human Emotions
? 3.2.1 Categorical Versus Dimensional Approaches
? 3.2.2 The Hourglass of Emotions
3.3 Sentic Medoids: Clustering Affective Common Sense Concepts
? 3.3.1 Partitioning Around Medoids
? 3.3.2 Centroid Selection
3.4 SlC4