Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation

  title={Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation},
  author={Kosetsu Tsukuda and Masataka Goto},
Online music services are increasing in popularity. They enable us to analyze people’s music listening behavior based on play logs. Although it is known that people listen to music based on topic (e.g., rock or jazz), we assume that when a user is addicted to an artist, s/he chooses the artist’s songs regardless of topic. Based on this assumption, in this paper, we propose a probabilistic model to analyze people’s music listening behavior. Our main contributions are three-fold. First, to the… 


Statistical models of music-listening sessions in social media
This paper shows how to define statistical models of different complexity to describe patterns of song listening in an online music community and defines a graphical model that takes into account listening sessions and captures the listening moods of users in the community.
Temporal Dynamics in Music Listening Behavior: A Case Study of Online Music Service
  • C. Park, Minsuk Kahng
  • Computer Science
    2010 IEEE/ACIS 9th International Conference on Computer and Information Science
  • 2010
A large sized real-world usage log data gathered from Bugs Music is analyzed and the result can be a useful guideline to the industry which delivers music items to users and tries to consider temporal context in their recommendations.
A Survey on Music Listening and Management Behaviours
The major findings of this survey show that elements such as familiarity of songs, how distracting they are, how much they match the listener’s mood, and the desire of changing the mood within one listening session, are all affected by the activity during which music is listened to.
Rocking around the clock eight days a week: an exploration of temporal patterns of music listening
It is shown that for certain users, artists and genres, temporal patterns of listening can be used to predict music listening selections with above-chance accuracy.
Improving Music Recommendation in Session-Based Collaborative Filtering by Using Temporal Context
This work compared two techniques to capture the users' listening patterns over time and found that the inclusion of temporal information, either explicitly or implicitly, increases significantly the accuracy of the recommendation, while compared to the traditional session-based CF.
Gendered scrobbling: Listening behavior of young adults on Last.fm
textabstractCombining insights from the psychology and sociology of music, this article addresses the extent to which the listening behaviour of young adults differs between men and women with regard
Listening factors: a large-scale principal components analysis of long-term music listening histories
An empirical analysis of long-term music listening histories from the last.fm web service gives insight into the most distinguishing factors in music listening behavior.
The LFM-1b Dataset for Music Retrieval and Recommendation
The LFM-1b dataset of more than one billion music listening events created by more than 120,000 users of Last.fm is presented, with its substantial size and a wide range of additional user descriptors that reflect their music taste and consumption behavior.
Session-Based Collaborative Filtering for Predicting the Next Song
  • Sung Eun Park, S. Lee, Sang-goo Lee
  • Computer Science
    2011 First ACIS/JNU International Conference on Computers, Networks, Systems and Industrial Engineering
  • 2011
This work proposes a simple but effective recommendation method for music recommender systems called Session-based Collaborative Filtering (SSCF), and looks into the different parameters that affect the recommendation accuracy.