%0 Journal Article %1 yahia2008efficient %A Yahia, Sihem Amer %A Benedikt, Michael %A Lakshmanan, Laks V. S. %A Stoyanovich, Julia %D 2008 %E Jagadish, H. V. %I VLDB Endowment %J Proceedings of the VLDB Endowment %K 2008 _todo collaboration folksonomy search social tagging web2.0 %N 1 %P 710--721 %R 10.1145/1453856.1453934 %T Efficient network aware search in collaborative tagging sites %U http://doi.acm.org/10.1145/1453856.1453934 %V 1 %X The popularity of collaborative tagging sites presents a unique opportunity to explore keyword search in a context where query results are determined by the opinion of a network of taggers related to a seeker. In this paper, we present the first in-depth study of network-aware search. We investigate efficient top-k processing when the score of an answer is computed as its popularity among members of a seeker's network. We argue that obvious adaptations of top-k algorithms are too space-intensive, due to the dependence of scores on the seeker's network. We therefore develop algorithms based on maintaining score upper-bounds. The global upper-bound approach maintains a single score upper-bound for every pair of item and tag, over the entire collection of users. The resulting bounds are very coarse. We thus investigate clustering seekers based on similar behavior of their networks. We show that finding the optimal clustering of seekers is intractable, but we provide heuristic methods that give substantial time improvements. We then give an optimization that can benefit smaller populations of seekers based on clustering of taggers. Our results are supported by extensive experiments on del.icio.us datasets.

@article{yahia2008efficient, abstract = {The popularity of collaborative tagging sites presents a unique opportunity to explore keyword search in a context where query results are determined by the opinion of a network of taggers related to a seeker. In this paper, we present the first in-depth study of network-aware search. We investigate efficient top-k processing when the score of an answer is computed as its popularity among members of a seeker's network. We argue that obvious adaptations of top-k algorithms are too space-intensive, due to the dependence of scores on the seeker's network. We therefore develop algorithms based on maintaining score upper-bounds. The global upper-bound approach maintains a single score upper-bound for every pair of item and tag, over the entire collection of users. The resulting bounds are very coarse. We thus investigate clustering seekers based on similar behavior of their networks. We show that finding the optimal clustering of seekers is intractable, but we provide heuristic methods that give substantial time improvements. We then give an optimization that can benefit smaller populations of seekers based on clustering of taggers. Our results are supported by extensive experiments on del.icio.us datasets.}, added-at = {2009-10-09T09:00:56.000+0200}, author = {Yahia, Sihem Amer and Benedikt, Michael and Lakshmanan, Laks V. S. and Stoyanovich, Julia}, biburl = {https://www.bibsonomy.org/bibtex/2b575923d842d924764bf58283bf9aeed/trude}, doi = {10.1145/1453856.1453934}, editor = {Jagadish, H. V.}, interhash = {27e08c3a4ec6c7dca673202735b8ecee}, intrahash = {b575923d842d924764bf58283bf9aeed}, journal = {Proceedings of the VLDB Endowment}, keywords = {2008 _todo collaboration folksonomy search social tagging web2.0}, month = {August}, number = 1, pages = {710--721}, publisher = {VLDB Endowment}, timestamp = {2009-10-29T23:56:08.000+0100}, title = {Efficient network aware search in collaborative tagging sites}, url = {http://doi.acm.org/10.1145/1453856.1453934}, volume = 1, year = 2008 }