Sarcasm is a term utilized by intelligent individuals on websites focused on blogs and social media. It is employed to convey the oblique information about the claims that are already trending on social media. Millions of people publish all kinds of judgmental or everyday opinions on this platform. And it gets quite difficult to tell if the remarks are compliments or jests; occasionally, it’s even tough for humans to tell. As a result, there is a greater requirement to identify sarcastic remarks in order to enhance autonomous sentiment analysis. it is practice of locating and gathering sarcastic remarks made by internet users in support of specific opinions or attitudes. A sarcasm detection system employs a variety of approaches, including context-based, rule- based, pattern dependent, and ML approaches. The system uses techniques including Support Vector Machine model, Random Forest, Naive Bayes model, with Maximum Entropy to assess the twitter dataset’s sarcasm identification and detection.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Understanding Sarcasm Online: Mechanisms, Challenges, and Impacts in Social Media Discourse

  • Yuvraj G. Nikam,
  • Vijay Pal Singh,
  • Dhanshri Amol Shinde

摘要

Sarcasm is a term utilized by intelligent individuals on websites focused on blogs and social media. It is employed to convey the oblique information about the claims that are already trending on social media. Millions of people publish all kinds of judgmental or everyday opinions on this platform. And it gets quite difficult to tell if the remarks are compliments or jests; occasionally, it’s even tough for humans to tell. As a result, there is a greater requirement to identify sarcastic remarks in order to enhance autonomous sentiment analysis. it is practice of locating and gathering sarcastic remarks made by internet users in support of specific opinions or attitudes. A sarcasm detection system employs a variety of approaches, including context-based, rule- based, pattern dependent, and ML approaches. The system uses techniques including Support Vector Machine model, Random Forest, Naive Bayes model, with Maximum Entropy to assess the twitter dataset’s sarcasm identification and detection.