Finding the Hidden Gems: Recommending Untagged Music
Abstract
We have developed a novel hybrid representation for Music Information Retrieval. Our representation is built by incorporating audio content into the tag space in a tag-track matrix, and then learning hybrid concepts using latent semantic analysis. We apply this representation to the task of music recommendation, using similarity-based retrieval from a query music track. We also develop a new approach to evaluating music recommender systems, which is based upon the relationship of users liking tracks. We are interested in measuring the recommendation quality, and the rate at which cold-start tracks are recommended. Our hybrid representation is able to outperform a tag-only representation, in terms of both recommendation quality and the rate that cold-start tracks are included as recommendations.
Cite
Text
Horsburgh et al. "Finding the Hidden Gems: Recommending Untagged Music." International Joint Conference on Artificial Intelligence, 2011. doi:10.5591/978-1-57735-516-8/IJCAI11-376Markdown
[Horsburgh et al. "Finding the Hidden Gems: Recommending Untagged Music." International Joint Conference on Artificial Intelligence, 2011.](https://mlanthology.org/ijcai/2011/horsburgh2011ijcai-finding/) doi:10.5591/978-1-57735-516-8/IJCAI11-376BibTeX
@inproceedings{horsburgh2011ijcai-finding,
title = {{Finding the Hidden Gems: Recommending Untagged Music}},
author = {Horsburgh, Ben and Craw, Susan and Massie, Stewart and Boswell, Robin},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2011},
pages = {2256-2261},
doi = {10.5591/978-1-57735-516-8/IJCAI11-376},
url = {https://mlanthology.org/ijcai/2011/horsburgh2011ijcai-finding/}
}