This work investigates personalized social search based on the user's social relations -- search results are re-ranked according to their relations with individuals in the user's social network. We study the effectiveness of several social network types for personalization: (1) Familiarity-based network of people related to the user through explicit familiarity connection; (2) Similarity-based network of people "similar" to the user as reflected by their social activity; (3) Overall network that provides both relationship types. For comparison we also experiment with Topic-based personalization that is based on the user's related terms, aggregated from several social applications. We evaluate the contribution of the different personalization strategies by an off-line study and by a user survey within our organization. In the off-line study we apply bookmark-based evaluation, suggested recently, that exploits data gathered from a social bookmarking system to evaluate personalized retrieval. In the on-line study we analyze the feedback of 240 employees exposed to the alternative personalization approaches. Our main results show that both in the off-line study and in the user survey social network based personalization significantly outperforms non-personalized social search. Additionally, as reflected by the user survey, all three SN-based strategies significantly outperform the Topic-based strategy.
%0 Conference Paper
%1 citeulike:6384936
%A Carmel, David
%A Zwerdling, Naama
%A Guy, Ido
%A Koifman, Shila O.
%A Har'el, Nadav
%A Ronen, Inbal
%A Uziel, Erel
%A Yogev, Sivan
%A Chernov, Sergey
%B Proceedings of the 18th ACM Conference on Information and Knowledge Management
%C New York, NY, USA
%D 2009
%I ACM
%K dlpaws, dppaws, social-network, social-search
%P 1227--1236
%R 10.1145/1645953.1646109
%T Personalized Social Search Based on the User's Social Network
%U http://dx.doi.org/10.1145/1645953.1646109
%X This work investigates personalized social search based on the user's social relations -- search results are re-ranked according to their relations with individuals in the user's social network. We study the effectiveness of several social network types for personalization: (1) Familiarity-based network of people related to the user through explicit familiarity connection; (2) Similarity-based network of people "similar" to the user as reflected by their social activity; (3) Overall network that provides both relationship types. For comparison we also experiment with Topic-based personalization that is based on the user's related terms, aggregated from several social applications. We evaluate the contribution of the different personalization strategies by an off-line study and by a user survey within our organization. In the off-line study we apply bookmark-based evaluation, suggested recently, that exploits data gathered from a social bookmarking system to evaluate personalized retrieval. In the on-line study we analyze the feedback of 240 employees exposed to the alternative personalization approaches. Our main results show that both in the off-line study and in the user survey social network based personalization significantly outperforms non-personalized social search. Additionally, as reflected by the user survey, all three SN-based strategies significantly outperform the Topic-based strategy.
%@ 978-1-60558-512-3
@inproceedings{citeulike:6384936,
abstract = {{This work investigates personalized social search based on the user's social relations -- search results are re-ranked according to their relations with individuals in the user's social network. We study the effectiveness of several social network types for personalization: (1) Familiarity-based network of people related to the user through explicit familiarity connection; (2) Similarity-based network of people "similar" to the user as reflected by their social activity; (3) Overall network that provides both relationship types. For comparison we also experiment with Topic-based personalization that is based on the user's related terms, aggregated from several social applications. We evaluate the contribution of the different personalization strategies by an off-line study and by a user survey within our organization. In the off-line study we apply bookmark-based evaluation, suggested recently, that exploits data gathered from a social bookmarking system to evaluate personalized retrieval. In the on-line study we analyze the feedback of 240 employees exposed to the alternative personalization approaches. Our main results show that both in the off-line study and in the user survey social network based personalization significantly outperforms non-personalized social search. Additionally, as reflected by the user survey, all three SN-based strategies significantly outperform the Topic-based strategy.}},
added-at = {2017-11-15T17:02:25.000+0100},
address = {New York, NY, USA},
author = {Carmel, David and Zwerdling, Naama and Guy, Ido and Koifman, Shila O. and Har'el, Nadav and Ronen, Inbal and Uziel, Erel and Yogev, Sivan and Chernov, Sergey},
biburl = {https://www.bibsonomy.org/bibtex/2b8f5ce5f953276e3ef287a2ca913ffac/brusilovsky},
booktitle = {Proceedings of the 18th ACM Conference on Information and Knowledge Management},
citeulike-article-id = {6384936},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1645953.1646109},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/1645953.1646109},
doi = {10.1145/1645953.1646109},
interhash = {7474e057085561fd0b067171a0a17191},
intrahash = {b8f5ce5f953276e3ef287a2ca913ffac},
isbn = {978-1-60558-512-3},
keywords = {dlpaws, dppaws, social-network, social-search},
location = {Hong Kong, China},
pages = {1227--1236},
posted-at = {2010-01-24 20:56:14},
priority = {5},
publisher = {ACM},
series = {CIKM '09},
timestamp = {2017-11-15T17:02:25.000+0100},
title = {{Personalized Social Search Based on the User's Social Network}},
url = {http://dx.doi.org/10.1145/1645953.1646109},
year = 2009
}