An Explanatory Matrix Factorization with User Comments Data

Matrix factorization is one of the crucial algorithms of the Recommendation system. It implies that the relationship between user and contents can be explained by hidden latent variables. However, it is not intuitive to understand the meaning of these hidden latent variables. Therefore, this study suggests a way to learn the meaning from supplementary data such as comments and use in matrix factorization. The data used in this study is user comment data from Naver which is the largest web platform and also the largest Webtoons (Web comics) platform in South Korea. We show that the suggest method which uses the supervised latent variable also fits well with users with the distinct tendency compare to conventional matrix factorization.