tagmusic / citymus

Repository for Spring 2017 semester project Music Recommendation in the City

CityMusic

The experience of a walk in the city with the most suitable soundtrack, on the base of the urban context.

DEMO - Slides

Abstract

Linked Data make possible the discovering of interesting connection between semantic entities that belongs to different domains. This report contains all the material we realised for developing cityMus, a web application that gives to the user the experience of a walk in the city with the most suitable soundtrack, on the base of the urban context. The application relies on a recommender system that search the shorter path in the graph between the Points of Interest (PoIs) nearby the user and music composers, making use of a combination of DBpedia and domain-specific datasets like 3cixty for tourism and DOREMUS for music metadata.

Content of the repository

Knowledge base matching

• match_3cixty_dbpedia Match PoIs between 3cixty and DBpedia.
• match_artist_doremus_spotify Match Artists between DOREMUS and Spotify.
• match_doremus_lod Match artists between DOREMUS and DBpedia/Wikidata -- see stats.
• spotify_analytic
• match_works_doremus_spotify Match DOREMUS works to Spotify tracks.
• youtube_experiment Use YouTube API for getting location related music videos.

Path finding

• path finder A script for computing the shortest paths in a RDF graph, in the form of a python notebook.

Application

• app The client application.
• server The recommender API server.

Other

• report The final report of the project (pdf).