SWDE : A Sub-Word And Document Embedding Based Engine for Clickbait Detection

TL;DR

This paper introduces a novel neural network-based engine that combines sub-word and document embeddings to effectively detect clickbait headlines, outperforming previous methods with an accuracy of 83.49%.

Contribution

It proposes a new multi-embedding approach using CNNs, BiLSTMs, attention, and Doc2Vec for improved clickbait detection.

Findings

Achieved 83.49% accuracy on clickbait detection.

Outperformed previous state-of-the-art methods.

Effectively combined sub-word and document embeddings.

Abstract

In order to expand their reach and increase website ad revenue, media outlets have started using clickbait techniques to lure readers to click on articles on their digital platform. Having successfully enticed the user to open the article, the article fails to satiate his curiosity serving only to boost click-through rates. Initial methods for this task were dependent on feature engineering, which varies with each dataset. Industry systems have relied on an exhaustive set of rules to get the job done. Neural networks have barely been explored to perform this task. We propose a novel approach considering different textual embeddings of a news headline and the related article. We generate sub-word level embeddings of the title using Convolutional Neural Networks and use them to train a bidirectional LSTM architecture. An attention layer allows for calculation of significance of each term towards the nature of the post. We also generate Doc2Vec embeddings of the title and article text and model how they interact, following which it is concatenated with the output of the previous component. Finally, this representation is passed through a neural network to obtain a score for the headline. We test our model over 2538 posts (having trained it on 17000 records) and achieve an accuracy of 83.49% outscoring previous state-of-the-art approaches.