An Emoticon-Based Novel Sarcasm Pattern Detection Strategy to Identify Sarcasm in Microblogging Social Networks

Department

Software Engineering and Game Development

Document Type

Article

Publication Date

1-1-2023

Abstract

Online social networks are one of the prime modes of communication used by people to voice their opinions and sentiments, especially after the advancement of digital gadgets and overall technology. Mining such sentiments and analyzing the polarity of user opinions is a trending research issue with high business value. Identifying, detecting, and understanding sarcasm is an important topic in the field of sentiment analysis. Despite being complex and challenging, automated detection of sarcasm is also a relatively less explored research area. In this article, we present a novel sarcasm pattern detection technique using emoticons to identify sarcasm in microblogging social networks like Twitter. Initially, we classify the tweets only with emoticons based on a decision tree classification approach. Afterward, we incorporate the SentiWordNet library and a separate emoticon library to find the polarities of the tokenized words and emoticons. Finally, we present a comparison of the polarity of the tweets and the polarity of the emoticons to detect sarcasm in tweets.

Journal Title

IEEE Transactions on Computational Social Systems

Journal ISSN

2329-924X

Digital Object Identifier (DOI)

10.1109/TCSS.2023.3306908

Share

COinS