Clickbait detection using word embeddings
This addresses the problem of identifying misleading content for online media platforms, but it is incremental as it applies an existing method to a specific domain.
The paper tackled clickbait detection in online news media by using word embeddings as features and training a linear regression model, achieving an F1-score of 64.98% and an MSE of 0.0791.
Clickbait is a pejorative term describing web content that is aimed at generating online advertising revenue, especially at the expense of quality or accuracy, relying on sensationalist headlines or eye-catching thumbnail pictures to attract click-throughs and to encourage forwarding of the material over online social networks. We use distributed word representations of the words in the title as features to identify clickbaits in online news media. We train a machine learning model using linear regression to predict the cickbait score of a given tweet. Our methods achieve an F1-score of 64.98\% and an MSE of 0.0791. Compared to other methods, our method is simple, fast to train, does not require extensive feature engineering and yet moderately effective.