A Neural Attentive Model Using Human Semantic Knowledge for Clickbait Detection

In this paper, we propose a neural attentive model using human semantic knowledge to detect clickbait. To the best of our knowledge, our work is the first that introduces a data enrichment method and incorporates human semantic knowledge for the purpose of clickbait detection. Experiments show that our approach, on two real-world datasets, not only achieves new state-of-the-art results but significantly outperforms existing systems by a large margin.