A tree-structured representation for book author and its recommendation using multilayer SOM

This paper introduces a new framework for author recommending using Multi-Layer Self-Organizing Map (ML-SOM). Concretely, an author is modeled by a tree-structured representation, and an MLSOM-based system is used as an efficient solution to the content-based author recommending problem. The tree-structured representation formulates author features in a hierarchy of author biography, written books and book comments. To efficiently tackle the tree-structured representation, we use an MLSOM algorithm that serves as a clustering technique to handle authors. The effectiveness of our approach was examined in a large-scale dataset containing 7426 authors, 205805 books they wrote, and 3027502 comments that readers have provided. The experimental results corroborate that the proposed approach outperforms current algorithms and can provide a promising solution to author recommendation.