Clickbait Detection via Contrastive Variational Modelling of Text and Label

Clickbait refers to deliberately created sensational or deceptive text for tricking readers into clicking, which severely hurts the web ecosystem. With a growing number of clickbaits on social media, developing automatic detection methods becomes essential. Nonetheless, the performance of existing neural classifiers is limited due to the underutilization of small labelled datasets. Inspired by related pedagogy theories that learning to write can promote comprehension ability, we propose a novel Contrastive Variational Modelling (CVM) framework to exploit the labelled data better. CVM models the distributions of text and clickbait labels simultaneously by predicting labels from text and generating text from labels jointly with Variational AutoEncoder and further distinguish the distributions with different labels by a contrastive learning loss. In this way, CVM can capture more underlying textual properties under each label and hence utilize label information to their full potential, boosting detection performance. We theoretically demonstrate CVM as learning a joint distribution of text, clickbait label, and latent variable. Experiments on three datasets show the superiority of our method over several recent strong baselines.