TiMers: Time-based music recommendation system based on social network services analysis

Esther Kim, Seung Yeon Kim, Ga Ae Kim, Mucheol Kim, Seungmin Rho*, Ka Lok Man, Woon Kian Chong

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

3 Citations (Scopus)

Abstract

Due to the explosive popularity of diverse social network services such as Twitter and Last.fm, they have become a practical and crucial source of information production and sharing it for a large number of users. For instance, Twitter is one of the biggest social networking services where a massive amount of instant messages have been published every day while Last.fm is a social music discovery service that provides personalized recommendations based on the music people listen to. In this paper, we analyzed several popular social network services (SNS) website for generating the music playlist based on the recommendation factors in terms of mood, genre and time. We performed as a case study for evaluating user satisfaction in music recommendation.

Original languageEnglish
Title of host publicationIMECS 2015 - International MultiConference of Engineers and Computer Scientists 2015
EditorsDavid Dagan Feng, S. I. Ao, Craig Douglas, S. I. Ao, Craig Douglas, Jeong-A Lee, S. I. Ao, Oscar Castillo
PublisherNewswood Limited
Pages741-742
Number of pages2
ISBN (Electronic)9789881925398
Publication statusPublished - 2015
EventInternational MultiConference of Engineers and Computer Scientists 2015, IMECS 2015 - Tsimshatsui, Kowloon, Hong Kong
Duration: 18 Mar 201520 Mar 2015

Publication series

NameLecture Notes in Engineering and Computer Science
Volume2
ISSN (Print)2078-0958

Conference

ConferenceInternational MultiConference of Engineers and Computer Scientists 2015, IMECS 2015
Country/TerritoryHong Kong
CityTsimshatsui, Kowloon
Period18/03/1520/03/15

Keywords

  • Music recommendation
  • Social network service

Fingerprint

Dive into the research topics of 'TiMers: Time-based music recommendation system based on social network services analysis'. Together they form a unique fingerprint.

Cite this