Music recommendation and discovery in the long tail

By Òscar Celma. 2008

345 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On the Effectiveness of Linear Models for One-Class Collaborative Filtering (2016, methodology): “We evaluated all methods on four datasets: (a) M L 1M, the MovieLens 1M dataset, (b) K OBO , an e-book purchase dataset from Rakuten Kobo Inc. 4 , (c) L AST FM, a song play count dataset from LastFM (Celma 2008), and (d) M SD , the Million Song dataset (Bertin-Mahieux et al. 2011).”
Fast ALS-based tensor factorization for context-aware recommendation from implicit feedback (2012, background): “The LastFM 1K [26] dataset contains listening habits of ∼1 000 users on songs of ∼170 000 artists (artists are considered items).”
Time-Dependent Representation for Neural Event Sequence Prediction (2017, methodology): “FM, 2009; Celma, 2010), we created a music recommendation sequence dataset.”
Recommendations : Modeling Music Ratings with Temporal Dynamics and Item Taxonomy (2011, background): “There are several approaches to music recommendations [6, 22]:”
Deep content-based music recommendation (2013, background): “the available items, because the users’ consumption patterns follow a power law [2].”
Diversity, Serendipity, Novelty, and Coverage (2016, methodology): “Although an item's unpopularity is not always a good indication of it being unknown—a user familiar with one rare item is likely to know similar rare items [Celma 2009]—it provides a cheap approximation for measuring novelty offline, without conducting costly user studies.”
A Time-Aware Exploration of RecSys15 Challenge Dataset (2016, background): “The distribution of the data motivates the use of recommender systems in this scenario, as they are known to enhance content discovery, and subsequently purchase, of items in the long tail [3].”
Time2Vec: Learning a Vector Representation of Time (2019, unknown): “FM users [7].”