Enriching Article Recommendation with Phrase Awareness
This work addresses content-based recommendation systems for users by enhancing feature informativeness and interpretability, though it appears incremental as it builds on existing deep learning methods.
The paper tackled the problem of article recommendation by injecting phrase-level features into content-based models to improve performance and interpretability, resulting in boosted predictions for user click and view behavior on real-world data.
Recent deep learning methods for recommendation systems are highly sophisticated. For article recommendation task, a neural network encoder which generates a latent representation of the article content would prove useful. However, using raw text with embedding for models could degrade sentence meanings and deteriorate performance. In this paper, we propose PhrecSys (Phrase-based Recommendation System), which injects phrase-level features into content-based recommendation systems to enhance feature informativeness and model interpretability. Experiments conducted on six months of real-world data demonstrate that phrase features boost content-based models in predicting both user click and view behavior. Furthermore, the attention mechanism illustrates that phrase awareness benefits the learning of textual focus by putting the model's attention on meaningful text spans, which leads to interpretable article recommendation.