DNCP: An attention-based deep learning approach enhanced with attractiveness and timeliness of News for online news click prediction

• Published in: Information & management 2021-03, Vol.58 (2), p.103428, Article 103428
• Main Authors: Xiong, Jie, Yu, Li, Zhang, Dongsong, Leng, Youfang
• Format: Article
• Language: English
• Subjects: Attention mechanism; Deep learning; News click prediction; Topic model
• ISSN: 0378-7206; 1872-7530
• DOI: 10.1016/j.im.2021.103428

•This study defines the concepts of attractiveness and timeliness of news and proposes new methods for representing them.•We propose a deep news click prediction (DNCP) method to integrate attractiveness, timeliness, and textual and meta features of news for news click prediction.•We enhance the attention representation of a news article based on the attractiveness and timeliness of individual terms contained in the article.•This study provides empirical evidence about the effectiveness of DNCP in news click prediction, providing novel technical and practical insights. Predicting news clicks or popularity is of great importance to news providers and recommender systems. Attractiveness and timeliness of news are two prominent drivers of news clicks. Attractiveness represents the appealingness or interestingness of news to an individual, while timeliness indicates the recency of news. Existing research on news click prediction models has ignored those two important variables. There is a lack of exploration and understanding of how to represent them in a predictive model and how effective and valuable they are to the prediction performance of a model. To fill these gaps, in this research, we propose a deep news click prediction (DNCP) model that integrates attractiveness and timeliness of news in an attention-based deep neural network for predicting news clicks. We also propose new measures for those two variables. Empirical evaluation using two real-world datasets shows that the DNCP model outperforms a variety of baseline models. The findings of this research provide several novel research contributions and practical implications for improving news click prediction.