In this article we address the challenge of detecting the generation and spreading of misleading information in the specific scenario of clickbait. Our contribution consists of a methodology that combines a deep neural network and an information divergence measure to overcome the limitations of deep learning techniques in this scenario. This analysis is conducted by considering a clickbait challenge dataset. We realise that the construction of the dataset used to study this kind of problems dramatically affects the performance of the model and, thus, its selection. Since clickbait is a result of the inconsistency between headlines and content, we integrate a divergence measure as a layer of a deep learning model. The resulting model overcomes the limitations of conventional machine learning and deep learning models in clickbait detection.
Christian Oliva , Ignacio Palacio-Marín, Luis F. Lago-Fernández, David Arroyo
ARES '22: Proceedings of the 17th International Conference on Availability, Reliability and Security