ICMR-Paper accepted

We got our paper Improving Context-Aware Music Recommender Systems: Beyond the Pre-filtering Approach accepted at the International Conference on Multimedia Retrieval (ICMR).

Abstract

Over the last years, music consumption has changed fundamentally: people switch from private, mostly limited music collections to huge public music collections provided by music streaming platforms. Thus, the amount of available music has increased dramatically and music streaming platforms heavily rely on recommender systems to assist users in discovering music they like. Incorporating the context of users has been shown to improve the quality of recommendations. Previous approaches based on pre-filtering suffered from a splitted dataset. In this work, we present a context-aware recommender system based on factorization machines that extracts information about the user's context from the names of the user's playlists. Based on a dataset comprising 15,000 users and 1.8 million tracks we show that our proposed approach outperforms the pre-filtering approach substantially in terms of accuracy of the computed recommendations.


BibTeX (Download)

@inproceedings{icmr2017,
title = {Improving Context-Aware Music Recommender Systems: Beyond the Pre-filtering Approach},
author = {Martin Pichl and Eva Zangerle and G\"{u}nther Specht},
url = {http://www.evazangerle.at/wp-content/uploads/2017/06/acm-icmr-2017.pdf},
doi = {10.1145/3078971.3078980},
year  = {2017},
date = {2017-06-07},
booktitle = {Proceedings of the 2017 ACM on International Conference on Multimedia  Retrieval, ICMR 2017, Bucharest, Romania},
pages = {201-208},
publisher = {ACM},
abstract = {Over the last years, music consumption has changed fundamentally: people switch from private, mostly limited music collections to huge public music collections provided by music streaming platforms. Thus, the amount of available music has increased dramatically and music streaming platforms heavily rely on recommender systems to assist users in discovering music they like. Incorporating the context of users has been shown to improve the quality of recommendations. Previous approaches based on pre-filtering suffered from a splitted dataset. In this work, we present a context-aware recommender system based on factorization machines that extracts information about the user's context from the names of the user's playlists. Based on a dataset comprising 15,000 users and 1.8 million tracks we show that  our proposed approach outperforms the pre-filtering approach substantially in terms of accuracy of the computed recommendations. },
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}