Paper Published in ICON’20 on Clickbait in Hindi Media

I am glad to inform you that our paper on clickbait in mainstream Hindi News Media has been accepted at the International Conference on Natural Language and Processing — 2020. You can find the abstract of the work we’ve done here, and the full paper is up on arxiv.


The proliferation of clickbait in Hindi media is just as severe as English. There isn’t a body of research on clickbait detection in Hindi yet, as against a lot of work done on clickbait in English media. It’s time to get started.


A corpus of Hindi news headlines shared on Twitter was created by collecting tweets of 5 mainstream Hindi news sources for a period of 4 months. 7 independent annotators were recruited to mark the 20 most retweeted news posts by each of the 5 news sources on its clickbait nature. The clickbait score hence generated was assessed for its correlation with interactions on the platform (retweets, favorites, reader replies), tweet word count, and normalized POS (part-of-speech) tag counts in tweets. A positive correlation was observed between readers’ interactions with tweets and tweets’ clickbait score. Significant correlations were also observed for POS tag counts and clickbait score. The prevalence of clickbait in mainstream Hindi news media was found to be similar to its prevalence in English news media. We hope that our observations would provide a platform for discussions on clickbait in mainstream Hindi news media.

Link to full paper

Feel free to get back to me with reviews/comments/questions on the paper. Would be happy to discuss it!

Originally published at on December 23, 2020.

Hacker | Engineer —

Hacker | Engineer —