Analysis of foul language usage in social media text conversation
by Sumit Kawate; Kailas Patil
International Journal of Social Media and Interactive Learning Environments (IJSMILE), Vol. 5, No. 3, 2017

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.

Online publication date: Mon, 13-Nov-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Social Media and Interactive Learning Environments (IJSMILE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com