Clickbait Detection with Style-aware Title Modeling and Co-attention

Clickbait Detection with Style-aware Title Modeling and Co-attention Chuhan Wu†, Fangzhao Wu‡, Tao Qi†, Yongfeng Huang† †Department of Electronic Engineering & BNRist, Tsinghua University, Beijing 100084, China ‡Microsoft Research Asia, Beijing 100080, China {wuchuhan15, wufangzhao, taoqi.qt}@gmail.com yfhuang@tsinghua.edu.cn Abstract Clickbait is a form of web content designed to attract attention and entice users to click on specific hyperlinks. The detection of clickbaits is an important task for online platforms to improve the quality of web content and the satisfaction of users. Clickbait detection is typically formed as a binary classification task based on the title and body of a webpage, and existing methods are mainly based on the content of title and the relevance between title and body. However, these methods ignore the stylistic patterns of titles, which can provide important clues on identifying clickbaits. In addition, they do not consider the interactions between the contexts within title and body, which are very important for measuring their relevance for clickbait detection. In this paper, we propose a clickbait detection approach with style-aware title modeling and co- attention. Specifically, we use Transformers to learn content representations of title and body, and respectively compute two content-based clickbait scores for title and body based on their representations. In addition, we propose to use a character-level Transformer to learn a style-aware title representation by capturing the stylistic patterns of title, and we compute a title stylistic score based on this representation. Besides, we propose to use a co-attention network to model the relatedness between the contexts within title and body, and further enhance their representations by encoding the interaction information. We compute a title-body matching score based on the representations of title and body enhanced by their interactions. The final clickbait score is predicted by a weighted summation of the aforementioned four kinds of scores. Extensive experiments on two benchmark datasets show that our approach can effectively improve the performance of clickbait detection and consistently outperform many baseline methods. 1 Introduction Clickbait is a type of web content that is designed to attract users’ attention and further entice them to click hyperlinks to enter specific webpages, such as news articles, advertisements and videos (Chakraborty et al., 2016). Several illustrative examples of clickbaits are shown in Fig. 1. We can see that the title of the first clickbait is written in a sensationalized way by using words with strong emotions like “MUST”, and the title of the second clickbait is misleading because it does not match the content of the body. Clickbaits are commonly used by online publishers, because clickbaits can draw more attention to the online websites where they are displayed and improve the revenue by attracting more clicks on advertisements (Dong et al., 2019). However, clickbaits are deceptive to users because the main content of clickbaits is often uninformative, misleading, or even irrelevant to the title, which is extremely harmful for the reading satisfaction of users (Chen et al., 2015). Thus, clickbait detection is an important task for online platforms to improve the quality …

Content truncated to 500 words