Deep Headline Generation for Clickbait Detection

Clickbaits are catchy social posts or sensational headlines that attempt to lure readers to click. Clickbaits are pervasive on social media and can have significant negative impacts on both users and media ecosystem. For example, users may be misled to receive inaccurate information, or fall into click-jacking attacks. Similarly, media platforms could lose readers' trust and revenues due to the prevalence of clickbaits. To computationally detect such clickbaits on social media using supervised learning framework, one of the major obstacles is the lack of large-scale labeled training data, due to laborious and costly labeling. With the recent advancements in deep generative models, to address this challenge, we propose to generate synthetic headlines with specific styles and explore their utilities to help improve clickbait detection. In particular, we propose to generate stylized headlines from original documents with style transfer. Furthermore, as it is non-trivial to generate stylized headlines due to several challenges such as the discrete nature of texts and the requirements of preserving semantic meaning of the document while achieving style transfer, we propose a novel solution, named as Stylized Headline Generation (SHG), that can not only generate readable and realistic headlines to enlarge original training data, but also helps improve the classification capacity of supervised learning. The experimental results on real-world datasets demonstrate the effectiveness of SHG on generating high-quality and high-utility headlines for clickbait detection.