TY - GEN
T1 - Exploiting various implicit feedback for collaborative filtering
AU - Yang, Byoungju
AU - Lee, Sangkeun
AU - Park, Sungchan
AU - Lee, Sang Goo
PY - 2012
Y1 - 2012
N2 - So far, many researchers have worked on recommender systems using users' implicit feedback, since it is difficult to collect explicit item preferences in most applications. Existing researches generally use a pseudo-rating matrix by adding up the number of item consumption; however, this naïve approach may not capture user preferences correctly in that many other important user activities are ignored. In this paper, we show that users' diverse implicit feedbacks can be significantly used to improve recommendation accuracy. We classify various users' behaviors (e.g., search item, skip, add to playlist, etc.) into positive or negative feedback groups and construct more accurate pseudo-rating matrix. Our preliminary experimental result shows significant potential of our approach. Also, we bring out a question to the previous approaches, aggregating item usage count into ratings. Copyright is held by the author/owner(s).
AB - So far, many researchers have worked on recommender systems using users' implicit feedback, since it is difficult to collect explicit item preferences in most applications. Existing researches generally use a pseudo-rating matrix by adding up the number of item consumption; however, this naïve approach may not capture user preferences correctly in that many other important user activities are ignored. In this paper, we show that users' diverse implicit feedbacks can be significantly used to improve recommendation accuracy. We classify various users' behaviors (e.g., search item, skip, add to playlist, etc.) into positive or negative feedback groups and construct more accurate pseudo-rating matrix. Our preliminary experimental result shows significant potential of our approach. Also, we bring out a question to the previous approaches, aggregating item usage count into ratings. Copyright is held by the author/owner(s).
KW - Implicit feedback
KW - Rating function
KW - Recommender system
KW - User behavior
UR - http://www.scopus.com/inward/record.url?scp=84861024088&partnerID=8YFLogxK
U2 - 10.1145/2187980.2188166
DO - 10.1145/2187980.2188166
M3 - Conference contribution
AN - SCOPUS:84861024088
SN - 9781450312301
T3 - WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion
SP - 639
EP - 640
BT - WWW'12 - Proceedings of the 21st Annual Conference on World Wide Web Companion
T2 - 21st Annual Conference on World Wide Web, WWW'12
Y2 - 16 April 2012 through 20 April 2012
ER -