In an age where people are becoming increasing likely to trust information found through online media, journalists have begun employing techniques to lure readers to articles by using catchy headlines, called clickbait. These headlines entice the user into clicking through the article whilst not providing information relevant to the headline itself. Previous methods of detecting clickbait have explored techniques heavily dependent on feature engineering, with little experimentation having been tried with neural network architectures. We introduce a novel model combining recurrent neural networks, attention layers and image embeddings. Our model uses a combination of distributed word embeddings derived from unannotated corpora, character level embeddings calculated through Convolutional Neural Networks. These representations are passed through a bidirectional LSTM with an attention layer. The image embeddings are also learnt from large data using CNNs. Experimental results show that our model achieves an F1 score of 65.37% beating the previous benchmark of 55.21%.
View on arXiv