Clickbait Identification using Neural Networks
This work addresses clickbait detection for online content moderation, but it is incremental as it applies existing neural network methods to a specific challenge.
The paper tackled clickbait identification by developing a neural network fusion system that generalizes across domains and languages without linguistic preprocessing, achieving a mean squared error of 0.0428, accuracy of 0.826, and F1 score of 0.564, ranking 6th out of 13 teams in the Clickbait Detection Challenge 2017.
This paper presents the results of our participation in the Clickbait Detection Challenge 2017. The system relies on a fusion of neural networks, incorporating different types of available informations. It does not require any linguistic preprocessing, and hence generalizes more easily to new domains and languages. The final combined model achieves a mean squared error of 0.0428, an accuracy of 0.826, and a F1 score of 0.564. According to the official evaluation metric the system ranked 6th of the 13 participating teams.