Book Recommendations Beyond the Usual Suspects: Embedding Book Plots Together with Place and Time Information
Here, we publish source code of our recommender system for books as part of our paper "Book Recommendations Beyond the Usual Suspects: Embedding Book Plots Together with Place and Time Information". It has been published at the International Conference On Asia-Pacific Digital Libraries (ICADL) 2018, where it also received the best paper award:
- Source Code: Link
- Movie dataset as extracted from Wikipedia: Link
- Paper: Link
Content-based recommendation of books and other media is usually based on semantic similarity measures. While metadata can be compared easily, measuring the semantic similarity of narrative literature is challenging. Keyword-based approaches are biased to retrieve books of the same series or do not retrieve any results at all in sparser libraries. We propose to represent plots with dense vectors to foster semantic search for similar plots even if they do not have any words in common. Further, we propose to embed plots, places, and times in the same embedding space. Thereby, we allow arithmetics on these aspects. For example, a book with a similar plot but set in a different, user-specified place can be retrieved. We evaluate our findings on a set of 16,000 book synopses that spans literature from 500 years and 200 genres and compare our approach to a keyword-based baseline.