Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Free Text In User Reviews: Their Role In Recommender Systems
AU - Terzi, Maria
AU - Ferrario, Maria
AU - Whittle, Jon
PY - 2011/10
Y1 - 2011/10
N2 - As short free text user-generated reviews become ubiquitous on the social web, opportunities emerge for new approaches torecommender systems that can harness users‟ reviews in open text form. In this paper we present a first experiment towards the development of a hybrid recommender system which calculates users‟ similarity based on the content of users‟ reviews. We apply this approach to the movie domain and evaluate the performance of LSA, a state-of-the-art similarity measure, at estimating users‟reviews similarity. Our initial investigation indicates that users‟similarity is not well reflected in traditional score-based recommender systems which solely rely on users‟ ratings. We argue that short free text reviews can be used as a complementary and effective information source. However, we also find that LSA underperforms when measuring the similarity of short, informal user-generated reviews. For this we argue that further research is needed to develop similarity measures better suited to noisy short text.
AB - As short free text user-generated reviews become ubiquitous on the social web, opportunities emerge for new approaches torecommender systems that can harness users‟ reviews in open text form. In this paper we present a first experiment towards the development of a hybrid recommender system which calculates users‟ similarity based on the content of users‟ reviews. We apply this approach to the movie domain and evaluate the performance of LSA, a state-of-the-art similarity measure, at estimating users‟reviews similarity. Our initial investigation indicates that users‟similarity is not well reflected in traditional score-based recommender systems which solely rely on users‟ ratings. We argue that short free text reviews can be used as a complementary and effective information source. However, we also find that LSA underperforms when measuring the similarity of short, informal user-generated reviews. For this we argue that further research is needed to develop similarity measures better suited to noisy short text.
KW - recommender systems
KW - text reviews
M3 - Conference contribution/Paper
SP - 45
EP - 48
BT - Proceedings of the 3rd ACM RecSys’10 Workshop on Recommender Systems and the Social Web. Chicago, US, October 2011
ER -