Title: Analysis of foul language usage in social media text conversation

Authors: Sumit Kawate; Kailas Patil

Addresses: Department of Computer Engineering, Vishwakarma Institute of Information Technology (VIIT), Pune, Maharashtra 411048, India ' Department of Computer Engineering, Vishwakarma Institute of Information Technology (VIIT), Pune, Maharashtra 411048, India

Abstract: The use of social media is the most common trend among the activities of today's people. Social networking sites offer today's teenagers a platform for communication and entertainment. They use social media to collect more information from their friends and followers. The vastness of social media sites ensures that not all of them provide a decent environment for children. In such cases, the impact of the negative influences of social media on teenage users increases with an increase in the use of offensive language in social conversations. This increase could lead to frustration, depression and a large change in their behaviour. Hence, we propose a novel approach to classify bad language usage in text conversations. We have considered the English and Marathi languages as the medium for textual conversation. We have developed our system based on a foul language classification approach; it is based on an improved version of a decision tree that detects offensive language usage in a conversation. As per our evaluation, we found that teenage user conversation is not decent all the time. We trained 3651 observations for six context categories using a Naïve Bayes algorithm for context detection. Then, the system classifies the use of foul language in one of the trained context in the text conversation. In our testbed, we observed 38% of participants used foul language during their text conversation. Hence, our proposed approach can identify the impact of foul language in text conversations using a classification technique and emotion detection to identify the foul language usage.

Keywords: children behaviour; context detection; cyber bullying; decision tree; depression; educators; emotion detection; foul language; hashing; interactive learning; issues and concerns with social media; naïve bayes; offensive language; sentiment analysis; social media; teenage users; trench.

DOI: 10.1504/IJSMILE.2017.087976

International Journal of Social Media and Interactive Learning Environments, 2017 Vol.5 No.3, pp.227 - 251

Received: 01 Apr 2017
Accepted: 04 Jul 2017
Published online: 13 Nov 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article