A Hybrid Approach to Service Recommendation Based on Network Representation LearningV5.0

  1892 users
   17632 artists
     
   12717 bi-directional user friend relations, i.e. 25434 (user_i, user_j) pairs
         avg. 13.443 friend relations per user
        
   92834 user-listened artist relations, i.e. tuples [user, artist, listeningCount]
         avg. 49.067 artists most listened by each user
         avg. 5.265 users who listened each artist
           
   11946 tags 
  
  186479 tag assignments (tas), i.e. tuples [user, tag, artist]
         avg. 98.562 tas per user
         avg. 14.891 tas per artist
         avg. 18.930 distinct tags used by each user
         avg. 8.764 distinct tags used for each artist