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

Citation Author(s):
Hao
Wu
Submitted by:
Hao Wu
Last updated:
Mon, 04/08/2019 - 07:38
DOI:
10.21227/419c-vx41
License:
49 Views
Categories:
Keywords:
0
0 ratings - Please login to submit your rating.

Abstract 

Abstract: 

A Hybrid Approach to Service Recommendation Based on Network Representation Learning

Instructions: 

  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

Dataset Files

ACCESS ON AWS

Documentation

AttachmentSize
Plain text icon tags.txt228.97 KB
Plain text icon user_artists.txt1.24 MB
Plain text icon user_friends.txt245.67 KB
Plain text icon user_taggedartists.txt4.16 MB
s