GBM Dataset

This dataset is a small subset of the data collected during the Great Black Music event (Paris, 2014) in the course of the AMMICO project. Visitors were equipped with devices allowing them to access multimedia content, and to "like" Point of Interests (POI, e.g. songs).

This dataset has been used in our paper:

[3] Ivan Keller and Emmanuel Viennet. Recommender systems for museums: Evaluation on a real dataset. In Fifth International Conference on Advances in Information Mining and Management, July 2015.

Please let me know if you use this data:

Download anonymized data file: GBM_favoris_raw_ano.txt.gz

The uncompressed file is a 45MB text consisting of an edge list of a bipartite graph (visitor_id x POI_id) representing the liked POIs (POI means Point Of Interest) for each visitor.

A small sample is:

sounds44 legende17_belafonte_136
sounds44 legende15_jackson_122
soweto44 legende1_kuti_9
soweto44 legende1_kuti_2
soweto44 legende1_kuti_5
soul44 legende15_jackson_117
soulsonic44 legende2_marley_12
soundiata44 legende2_marley_13
startin44 legende1_kuti_6
soul44 addis_maputo_263
spangled44 legende16_franco_133