Conducting sentiment analysis / Lei Lei, Dilin Liu.

Format:

Book

Author/Creator:

Lei, Lei, 1981- author.

Liu, Dilin, author.

Series:

Cambridge elements. Elements in corpus linguistics, 2632-8097.

Cambridge elements. Elements in corpus linguistics, 2632-8097

Language:

English

Subjects (All):

Natural language processing (Computer science).

Computational linguistics.

Sentiment analysis.

Physical Description:

1 online resource (104 pages) : digital, PDF file(s).

Edition:

1st ed.

Place of Publication:

Cambridge : Cambridge University Press, 2021.

Summary:

This Element provides a basic introduction to sentiment analysis, aimed at helping students and professionals in corpus linguistics to understand what sentiment analysis is, how it is conducted, and where it can be applied. It begins with a definition of sentiment analysis and a discussion of the domains where sentiment analysis is conducted and used the most. Then, it introduces two main methods that are commonly used in sentiment analysis known as "supervised machine-learning" and "unsupervised learning (or lexicon-based)" methods, followed by a step-by-step explanation about how to perform sentiment analysis with R. The Element then provides two detailed examples or cases of sentiment and emotion analysis, with one using an unsupervised method and the other using a supervised learning method.

Contents:

Cover

Title page

Copyright page

Conducting Sentiment Analysis

Contents

1 Sentiment Analysis: Background

1.1 Definition and Description of Sentiment Analysis

1.2 Sentiment Analysis vs. Appraisal, Stance, and Semantic Prosody

1.3 Existing Work of Sentiment Analysis: Major Domains/Topics, Successes, Challenges/Questions, and Principles

1.3.1 Major Domains and Topics

1.3.2 Successes and Challenges

1.3.3 Key Principles

1.4 Summary

2 Methods for Sentiment Analysis

2.1 Overview

2.2 Unsupervised Machine-Learning/Lexicon-Based Methods

2.3 Supervised Machine-Learning Methods

2.4 A Comparison of the Methods

2.5 Challenges and Responses

2.6 Summary

3 How to Do Sentiment Analysis with R

3.1 Supervised Machine-Learning Sentiment Analysis with R

3.1.1 Process of Supervised Machine-Learning Sentiment Analysis

3.1.2 Doing Supervised Machine-Learning Sentiment Analysis with R

3.2 Unsupervised/Lexicon-Based Sentiment Analysis

3.2.1 Rationale of Unsupervised/Lexicon-Based Sentiment Analysis

3.2.2 Doing Unsupervised/Lexicon-Based Sentiment Analysis with R

3.3 Unsupervised/Lexicon-Based Emotion Analysis

3.3.1 Rationale of Unsupervised/Lexicon-Based Emotion Analysis

3.3.2 Doing Unsupervised/Lexicon-Based Emotion Analysis with R

3.4 Summary

4 Case Study 1: A Diachronic Analysis of Sentiments and Emotions in the State of the Union Addresses

4.1 Background

4.1.1 The SOTUs and Reasons for a Diachronic Sentiment/Emotion Analysis of Them

4.1.2 Existing Research on SOTUs

4.1.3 Research Purposes and Questions

4.2 Methods

4.2.1 Data

4.2.2 Data Processing and Analysis

4.3 Results and Discussion

4.3.1 Sentiment Analysis

4.3.2 Emotion Analysis

4.4 Summary

5 Case Study 2: A Sentiment and Emotion Analysis of Movie Reviews

5.1 Background.

5.1.1 Existing Research

5.1.2 Challenges in Aspect-Level Analysis

5.1.3 Purposes of the Present Study

5.2 Methods

5.2.1 The Data

5.2.2 The Procedures of Data Processing

5.3 Results and Discussion

5.3.1 Supervised Machine-Learning Sentiment Analysis of Movie Reviews

5.3.2 Aspect-Level Emotion Analysis of Movie Reviews

5.4 Summary

6 Conclusion: Where We Are and Where We Are Heading

References.

Notes:

Title from publisher's bibliographic system (viewed on 31 Aug 2021).

ISBN:

1-108-90469-6

1-108-90569-2

1-108-90967-1

OCLC:

1267430132