MuSe: The Musical Sentiment Dataset

The MuSe (Music Sentiment) dataset contains sentiment information for 90,408 songs. We computed scores for the affective dimensions of <em>valence</em>, <em>dominance</em> and <em>arousal</em>, based on the user-generated tags that are available for each song via Last.fm. In addition, we provide artist and title metadata as well as a Spotify ID and a MusicBrainz ID, which allow researchers to extend the dataset with further metadata, such as genre or year. Though the tags themselves cannot be included in the dataset, we include a jupyter notebook in our accompanying Github repository that demonstrates how to fetch the tags of a given song from the Last.fm API (Last.fm_API.ipynb) We further include a jupyter notebook in the same repository that demonstrates how one might enrich the dataset with audio features using different endpoints of the Spotify API using the included Spotify IDs (spotify_API.ipynb). Please note that in its current form, the dataset only contains tentative spotify IDs for a subset (around 68%) of the songs.

MuSe（音乐情感，Music Sentiment）数据集收录了90408首歌曲的情感信息。我们基于每首歌曲在Last.fm平台上的用户生成标签，计算了效价（valence）、支配性（dominance）与唤醒度（arousal）三个情感维度的得分。此外，数据集还附带艺术家与曲目名称元数据，以及Spotify ID和MusicBrainz ID，便于研究人员为数据集补充流派、发行年份等更多元数据。由于原始标签无法纳入数据集，我们在配套的GitHub仓库中提供了Jupyter Notebook文件（Last.fm_API.ipynb），演示如何通过Last.fm API获取指定歌曲的标签。我们还在同一仓库中提供了另一款Jupyter Notebook文件（spotify_API.ipynb），展示如何利用数据集附带的Spotify ID，通过Spotify API的不同接口为数据集补充音频特征。请注意，当前版本的数据集仅为约68%的歌曲提供了暂用Spotify ID。