Using Posters to Recommend Anime and Mangas in a Cold-Start Scenario
This addresses the cold-start issue for anime and manga recommender systems, offering a practical solution with interpretable results, though it is incremental as it builds on existing collaborative filtering techniques.
The paper tackled the item cold-start problem in anime and manga recommendations by using deep learning to extract tag information from posters and proposing a new collaborative filtering model, BALSE, which improved recommendation quality, especially for less-known manga, and provided user taste interpretation.
Item cold-start is a classical issue in recommender systems that affects anime and manga recommendations as well. This problem can be framed as follows: how to predict whether a user will like a manga that received few ratings from the community? Content-based techniques can alleviate this issue but require extra information, that is usually expensive to gather. In this paper, we use a deep learning technique, Illustration2Vec, to easily extract tag information from the manga and anime posters (e.g., sword, or ponytail). We propose BALSE (Blended Alternate Least Squares with Explanation), a new model for collaborative filtering, that benefits from this extra information to recommend mangas. We show, using real data from an online manga recommender system called Mangaki, that our model improves substantially the quality of recommendations, especially for less-known manga, and is able to provide an interpretation of the taste of the users.