The dataset is built by exploiting the Spotify and SoundCloud APIs. It is composed of over 14,500 different songs of both famous and less famous Italian musicians. Each song in the dataset is identified by its Spotify id and its title. Tracks' metadata include also lemmatized and POS-tagged lyrics and, in the most of cases, ten musical features directly gathered from Spotify. Musical features include acousticness (float), danceability (float), duration_ms (int), energy (float), instrumentalness (float), liveness (float), loudness (float), speechiness (float), tempo (float) and valence (float). All features range from 0.0 to 1.0 except for loudness that typically ranges between -60 and 0 db, the tempo that represents beats per minute (BPM) and the duration that represents the track in milliseconds. For further information refer to the Spotify's documentation at https://developer.spotify.com/documentation/web-api/reference/tracks/get-audio-features/. Moreover, every song is enriched with information regarding its artist, such as the Spotify id, name, music genre, region of provenance and its popularity score. In particular, the artists' genre belongs to one of the 11 major music genres identified by using lists of popular music genres gathered from AllMusic and Wikipedia. Major music genres are limited to latin, classical, jazz, pop, blues, electronic, folk, light music, R&B, hip-hop, and rock.