Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | RecSys'09 |
| Untertitel | Proceedings of the 3rd ACM Conference on Recommender Systems |
| Seiten | 61-68 |
| Seitenumfang | 8 |
| Publikationsstatus | Veröffentlicht - 23 Okt. 2009 |
| Veranstaltung | 3rd ACM Conference on Recommender Systems, RecSys'09 - New York, NY, USA / Vereinigte Staaten Dauer: 23 Okt. 2009 → 25 Okt. 2009 |
Publikationsreihe
| Name | RecSys'09 - Proceedings of the 3rd ACM Conference on Recommender Systems |
|---|
Abstract
Tagging systems have become major infrastructures on the Web. They allow users to create tags that annotate and categorize content and share them with other users, very helpful in particular for searching multimedia content. However, as tagging is not constrained by a controlled vocabulary and annotation guidelines, tags tend to be noisy and sparse. Especially new resources annotated by only a few users have often rather idiosyncratic tags that do not reflect a common perspective useful for search. In this paper we introduce an approach based on Latent Dirichlet Allocation (LDA) for recommending tags of resources in order to improve search. Resources annotated by many users and thus equipped with a fairly stable and complete tag set are used to elicit latent topics to which new resources with only a few tags are mapped. Based on this, other tags belonging to a topic can be recommended for the new resource. Our evaluation shows that the approach achieves significantly better precision and recall than the use of association rules, suggested in previous work, and also recommends more specific tags. Moreover, extending resources with these recommended tags significantly improves search for new resources.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Angewandte Informatik
- Informatik (insg.)
- Software
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
RecSys'09: Proceedings of the 3rd ACM Conference on Recommender Systems. 2009. S. 61-68 (RecSys'09 - Proceedings of the 3rd ACM Conference on Recommender Systems).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Latent Dirichlet allocation for tag recommendation
AU - Krestel, Ralf
AU - Fankhauser, Peter
AU - Nejdl, Wolfgang
PY - 2009/10/23
Y1 - 2009/10/23
N2 - Tagging systems have become major infrastructures on the Web. They allow users to create tags that annotate and categorize content and share them with other users, very helpful in particular for searching multimedia content. However, as tagging is not constrained by a controlled vocabulary and annotation guidelines, tags tend to be noisy and sparse. Especially new resources annotated by only a few users have often rather idiosyncratic tags that do not reflect a common perspective useful for search. In this paper we introduce an approach based on Latent Dirichlet Allocation (LDA) for recommending tags of resources in order to improve search. Resources annotated by many users and thus equipped with a fairly stable and complete tag set are used to elicit latent topics to which new resources with only a few tags are mapped. Based on this, other tags belonging to a topic can be recommended for the new resource. Our evaluation shows that the approach achieves significantly better precision and recall than the use of association rules, suggested in previous work, and also recommends more specific tags. Moreover, extending resources with these recommended tags significantly improves search for new resources.
AB - Tagging systems have become major infrastructures on the Web. They allow users to create tags that annotate and categorize content and share them with other users, very helpful in particular for searching multimedia content. However, as tagging is not constrained by a controlled vocabulary and annotation guidelines, tags tend to be noisy and sparse. Especially new resources annotated by only a few users have often rather idiosyncratic tags that do not reflect a common perspective useful for search. In this paper we introduce an approach based on Latent Dirichlet Allocation (LDA) for recommending tags of resources in order to improve search. Resources annotated by many users and thus equipped with a fairly stable and complete tag set are used to elicit latent topics to which new resources with only a few tags are mapped. Based on this, other tags belonging to a topic can be recommended for the new resource. Our evaluation shows that the approach achieves significantly better precision and recall than the use of association rules, suggested in previous work, and also recommends more specific tags. Moreover, extending resources with these recommended tags significantly improves search for new resources.
KW - Delicious
KW - Social bookmarking system
KW - Tag recommendation
KW - Tag search
UR - http://www.scopus.com/inward/record.url?scp=72249122753&partnerID=8YFLogxK
U2 - 10.1145/1639714.1639726
DO - 10.1145/1639714.1639726
M3 - Conference contribution
AN - SCOPUS:72249122753
SN - 9781605584355
T3 - RecSys'09 - Proceedings of the 3rd ACM Conference on Recommender Systems
SP - 61
EP - 68
BT - RecSys'09
T2 - 3rd ACM Conference on Recommender Systems, RecSys'09
Y2 - 23 October 2009 through 25 October 2009
ER -