synffsynff is a music discovery system built around artist lineage, editorial context, and semantic album profiles.
Most music services describe taste through plays, skips, genre labels, and sonic similarity. synff starts somewhere else: the artists a listener keeps returning to, the albums they collect, and the public language around records that gives music a vocabulary.
The result is music recommendation with memory. A recommendation should give a listener a record worth hearing, and also a reason that record belongs in the path they are already following.
Artist lineage describes relationships between musicians, scenes, influences, collaborators, peers, and reference points. In synff, lineage gives listeners context for why one artist can lead naturally to another, without reducing discovery to listening-history lookalikes.
Music writing gives listeners a shared language for records: scene, reference point, craft, atmosphere, and reception. synff treats that public conversation as context for discovery, so recommendations can carry meaning beyond metadata.
A semantic album profile is a high-level description of how a record is understood in language. It helps describe the character and feeling of an album without relying only on genre labels or acoustic resemblance.
A good recommendation should offer more than a nearby sound. synffis shaped around records with a reason, a route in, and a place inside the listener's taste.
Music is art, and the people who make it should be paid for that work.synff shows estimated payout context beside listening and direct purchase options so a stream, a save, and a record bought from an artist can be understood as different kinds of support.
Audio similarity can find recordings that sound alike. Genre taxonomies can organise style names. synff is more interested in context: relationships around artists, language around albums, and the choices a listener keeps making.
Artist lineage means the documented relationships around an artist: influences, peers, scenes, collaborators, descendants, and reference points. It is useful for music discovery because it gives listeners context for why one artist leads naturally to another.
Semantic music discovery uses meaning around music, not only audio features or genre labels. In synff, semantic album profiles describe the character of records through high-level language and editorial context.
Genre can be useful context, but synff does not treat a deep genre taxonomy as the main model of taste. Artist lineage and album context matter more than a genre tree.
synff is not centred on audio similarity. Audio resemblance can be useful, but synffis built around artist relationships, album context, and the listener's own saved taste.
Elena Badillo-Goicoechea
Modeling Artist Influence for Music Selection and Recommendation: A Purely Network-Based Approach, review-based artist networks and recommendation.
Sungenre
Sungenre, music discovery by artist influence, genre, and location.
Pasi Saari and Tuomas Eerola
Semantic Computing of Moods Based on Tags in Social Media of Music, semantic mood representation from music-related tags.