Distance- and Rank-based Music Mainstreaminess Measurement
M. Schedl, and C. Bauer. 2nd Workshop on Surprise, Opposition, and Obstruction in Adaptive and Personalized Systems, in conjunction with 25th International Conference on User Modeling, Adaptation and Personalization (UMAP 2017), page 364-367. New York, NY, USA, ACM, (July 2017)
DOI: 10.1145/3099023.3099098
Abstract
A music listener's mainstreaminess indicates the extent to which her listening preferences correspond to those of the population at large. However, formal definitions to quantify the level of mainstreaminess of a listener are rare and those available define mainstreaminess based on fractions between some kind of individual and global listening profiles. We argue, in contrast, that measures based on a modified version of the well-established Kullback-Leibler (KL) divergence as well as rank-order correlation coefficient may be better suited to capture the mainstreaminess of listeners. We therefore propose two measures adopting KL divergence and rank-order correlation and show, on a real-world dataset of over one billion user-generated listening events (LFM-1b), that music recommender systems can notably benefit when grouping users according to their level of mainstreaminess with respect to these two measures. This particularly holds for the frequently neglected listener group which is characterized by low mainstreaminess.
2nd Workshop on Surprise, Opposition, and Obstruction in Adaptive and Personalized Systems, in conjunction with 25th International Conference on User Modeling, Adaptation and Personalization (UMAP 2017)
year
2017
month
July
pages
364-367
publisher
ACM
series
SOAP 2017
type
Conference Proceedings
venue
Bratislava, Slovakia
isbn
978-1-4503-5067-9/17/07
language
English
eventdate
9 July 2017
eventtitle
2nd Workshop on Surprise, Opposition, and Obstruction in Adaptive and Personalized Systems, in conjunction with 25th International Conference on User Modeling, Adaptation and Personalization (UMAP 2017)
%0 Conference Paper
%1 soap2017_distance_rank
%A Schedl, Markus
%A Bauer, Christine
%B 2nd Workshop on Surprise, Opposition, and Obstruction in Adaptive and Personalized Systems, in conjunction with 25th International Conference on User Modeling, Adaptation and Personalization (UMAP 2017)
%C New York, NY, USA
%D 2017
%E Bieliková, Mária
%E Herder, Eelco
%E Cena, Federica
%E Desmarais, Michel C.
%I ACM
%K imported mainstreaminess music myown recsys
%P 364-367
%R 10.1145/3099023.3099098
%T Distance- and Rank-based Music Mainstreaminess Measurement
%U http://dblp.uni-trier.de/db/conf/um/umap2017a.html#SchedlB17
%X A music listener's mainstreaminess indicates the extent to which her listening preferences correspond to those of the population at large. However, formal definitions to quantify the level of mainstreaminess of a listener are rare and those available define mainstreaminess based on fractions between some kind of individual and global listening profiles. We argue, in contrast, that measures based on a modified version of the well-established Kullback-Leibler (KL) divergence as well as rank-order correlation coefficient may be better suited to capture the mainstreaminess of listeners. We therefore propose two measures adopting KL divergence and rank-order correlation and show, on a real-world dataset of over one billion user-generated listening events (LFM-1b), that music recommender systems can notably benefit when grouping users according to their level of mainstreaminess with respect to these two measures. This particularly holds for the frequently neglected listener group which is characterized by low mainstreaminess.
%@ 978-1-4503-5067-9/17/07
@inproceedings{soap2017_distance_rank,
abstract = {A music listener's mainstreaminess indicates the extent to which her listening preferences correspond to those of the population at large. However, formal definitions to quantify the level of mainstreaminess of a listener are rare and those available define mainstreaminess based on fractions between some kind of individual and global listening profiles. We argue, in contrast, that measures based on a modified version of the well-established Kullback-Leibler (KL) divergence as well as rank-order correlation coefficient may be better suited to capture the mainstreaminess of listeners. We therefore propose two measures adopting KL divergence and rank-order correlation and show, on a real-world dataset of over one billion user-generated listening events (LFM-1b), that music recommender systems can notably benefit when grouping users according to their level of mainstreaminess with respect to these two measures. This particularly holds for the frequently neglected listener group which is characterized by low mainstreaminess.},
added-at = {2019-04-27T18:20:03.000+0200},
address = {New York, NY, USA},
author = {Schedl, Markus and Bauer, Christine},
biburl = {https://www.bibsonomy.org/bibtex/273403c1488f7cdb4710c43cdb4e5b2ab/bauerc},
booktitle = {2nd Workshop on Surprise, Opposition, and Obstruction in Adaptive and Personalized Systems, in conjunction with 25th International Conference on User Modeling, Adaptation and Personalization (UMAP 2017)},
doi = {10.1145/3099023.3099098},
editor = {Bieliková, Mária and Herder, Eelco and Cena, Federica and Desmarais, Michel C.},
eventdate = {9 July 2017},
eventtitle = {2nd Workshop on Surprise, Opposition, and Obstruction in Adaptive and Personalized Systems, in conjunction with 25th International Conference on User Modeling, Adaptation and Personalization (UMAP 2017)},
interhash = {fd17dc954338c409d16cc192ed9c2b4a},
intrahash = {73403c1488f7cdb4710c43cdb4e5b2ab},
isbn = {978-1-4503-5067-9/17/07},
keywords = {imported mainstreaminess music myown recsys},
language = {English},
month = {July},
pages = {364-367},
publisher = {ACM},
series = {SOAP 2017},
timestamp = {2020-06-14T02:15:10.000+0200},
title = {Distance- and Rank-based Music Mainstreaminess Measurement},
type = {Conference Proceedings},
url = {http://dblp.uni-trier.de/db/conf/um/umap2017a.html#SchedlB17},
venue = {Bratislava, Slovakia},
year = 2017
}