Clickbait Detection Based on Word Embedding Models

Abstract

In recent years, social networking platform serves as a new media of news sharing and information diffusion. Social networking platform has become a part of our daily life. As such, social media advertising budgets have explosively expanded worldwide over the past few years. Due to the huge commercial interest, clickbait behaviors are commonly observed, which use attractive headlines and sensationalized textual description to bait users to visit websites. Clickbaits mainly exploit the users’ curiosity’s gap by interesting headlines to entice its readers to click an accompanying link to articles often with poor contents. Clickbaits are bothersome either to social media users or platform site owners. In this paper, we propose an approach called Ontology-based LSTM Model (OLSTM) to detect clickbaits. Compared with the existing solutions for clickbait detection, our approach is characterized by the following three components: word embedding model, Recurrent Neural Networks (RNN), and word ontology information. The observation is that preserving semantic relationships is significantly an important factor to be considered in detecting clickbaits. Therefore, we propose to capture semantic relationships between words by word embedding models. In addition, we adopted RNN as our classification models to consider word orders in a sentence. Furthermore, we consider the word ontology relation as another feature set for clickbait classification, as clickbaits often uses words with generalized concepts to induce curiosity. We conduct experiments with real data from Twitter and news websites to validate the effectiveness of the proposed approach, which demonstrates that the employment of the proposed method improves clickbait detection accuracy from 80% to 90% compared with the existing solutions.