Popularity Bias in Music Recommendations
随着越来越多的音乐通过音乐流服务获得,音乐推荐系统对于帮助用户搜索,分类和过滤广泛的音乐收藏已成为必不可少的音乐。
Beyond-mainstream listeners receive worse music recommendations than mainstream listeners
但是,推荐系统容易受欢迎,这是一个众所周知的问题,这导致长尾项目(即用户互动很少的项目)很少被推荐。
我们通过衡量主流音乐和超级主流音乐的听众的算法生成音乐建议的准确性来验证这种效果。
We used a dataset containing the listening histories of 4,148 users (2,074 users in each group) of the music streaming platform Last.fm who listened mostly to beyond-mainstream music (Beyms)或主要是主流音乐(MS)。
图1显示,超越主流听众的音乐建议比主流听众更糟糕。
Subgroups of Beyond-Mainstream Music Listeners
我们应用了无监督的聚类算法HDBSCAN*来识别超级主流音乐听众中的子组。
We identified four subgroups, which we labeled according to the types of music they most frequently listened to: (i) users of music genres with only acoustic instruments such as folk (U_folk),(ii)高能音乐的用户,例如硬摇滚或嘻哈音乐(U_hard),,,,((iii) users of music with acoustic instruments and (nearly) no vocals such as ambient (U_AMBI)和(iv)高能量音乐的用户,没有(几乎)没有人声(例如Electronica)(U_ELEC)。
对音乐建议的影响
听音乐的用户意愿的外在要求e their own music preferences has a positive effect on the quality of music recommendations
By comparing each subgroup’s listening histories, we identified users who were most likely to listen to music outside their preferred genres.
那些主要听过声学的人(几乎)没有人声,例如U_AMBI发现)最有可能听取其他亚组首选的音乐。
那些主要听高能音乐的人,例如硬摇滚或嘻哈音乐(U_hard)最不可能听其他亚组首选的音乐。
In figure 2 below we see thatU_AMBIreceives better recommendations thanU_hard,,,,which means that the willingness of users to listen to music outside their own main music preferences has a positive effect on the quality of music recommendations.
Towards Fair Music Recommendations
我们认为,我们的发现为开发改进的用户模型和推荐方法提供了宝贵的见解,以更好地为主流音乐听众提供服务。
但是,我们还认为,仍然需要进行大量研究来提供公平的音乐推荐模型,这些模型可推广,并避免对任何用户组的不公平处理。
我们希望我们的数据集(https://doi.org/10.5281/Zenodo.3784764)and source code (https://github.com/pmuellner/supporttheunderground)provided with the article are of use to the scientific community for future analyses.
Comments