Encyclopedia
Please note this is a comparison between Version 1 by Joyce Y.M. Nip and Version 2 by Camila Xu.
Social media sentiment analysis is the computational detection and extraction of human subjective evaluation of objects embedded on social media. Previous sentiment analysis was conducted on isolated written texts, and typically classified sentiment into positive, negative, and neutral states. Social media sentiment analysis has included multi-modal texts, temporal dynamics, interactions, network relationships, and sentiment propagation. Specific emotions and sentiment intensity are also detected.
- artificial intelligence
- aspect-based sentiment analysis
- deep learning
- knowledge graphs
- large language models
- machine learning
- multi-modal analysis
- natural language processing
- sentiment
- social media
1. Introduction
Sentiment analysis began as a field in computer science and has since extended into social sciences and management studies. Because emotions, cognition, and behavior are interconnected, sentiment analysis can help researchers to understand individual attitudes and predict human behaviors, as well as inform remedial and preventive actions at the individual and societal levels. Sentiment can be taken to refer to the feeling that underlies an expressed positive or negative opinion or the feeling implied by a neutral opinion. It is therefore also called opinion mining [1]. As summed up by [2], a feeling is “a sensation that has been checked against previous experiences and labelled” while an emotion is “the projection/display of a feeling”. This entry focuses on social media sentiment analysis, a field that has grown in prominence within both academia and industry due to the increasing prevalence of social media in everyday life. It explains its genesis, discusses its applications, identifies its types, features and approaches. It concludes with a discussion on emerging developments in Large Language Models and future challenges.
