Christine Bauer,
"Allowing for equal opportunities for artists in music recommendation"
: Proceedings of the 1st Workshop on Designing Human-Centric MIR Systems (wsHCMIR 2019), satellite event to 20th annual conference of the International Society for Music Information Retrieval, 2019
Original Titel:
Allowing for equal opportunities for artists in music recommendation
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the 1st Workshop on Designing Human-Centric MIR Systems (wsHCMIR 2019), satellite event to 20th annual conference of the International Society for Music Information Retrieval
Original Kurzfassung:
Promoting diversity in the music sector is widely discussed
on the media. While the major problem may lie deep in
our society, music information retrieval contributes to promoting
diversity or may create unequal opportunities for
artists. For example, considering the known problem of
popularity bias in music recommendation, it is important to
investigate whether the short head of popular music artists
and the long tail of less popular ones show similar patterns
of diversity?in terms of, for example, age, gender, or ethnic
origin?or the popularity bias amplifies a positive or
negative effect.
I advocate for reasonable opportunities for artists?
for (currently) popular artists and artists in the long-tail
alike?in music recommender systems. In this work, I represent
the position that we need to develop a deep understanding
of the biases and inequalities because it is the essential
basis to design approaches for music recommendation
that provide reasonable opportunities. Thus, research
needs to investigate the various reasons that hinder equal
opportunity and diversity in music recommendation.