To improve the search results for socially-connect users, we propose a ranking framework, Social Network Document Rank (SNDocRank). This framework considers both document contents and the similarity between a searcher and document owners in a social network and uses a Multi-level Actor Similarity (MAS) algorithm to efficiently calculate user similarity in a social network. Our experiment results based on YouTube data show that compared with the tf-idf algorithm, the SNDocRank method returns more relevant documents of interest. Our findings suggest that in this framework, a searcher can improve search by joining larger social networks, having more friends, and connecting larger local communities in a social network.
%0 Conference Paper
%1 citeulike:13839839
%A Gou, Liang
%A Chen, Hung H.
%A Kim, Jung H.
%A Zhang, Xiaolong L.
%A Giles, C. Lee
%B Proceedings of the 19th International Conference on World Wide Web
%C New York, NY, USA
%D 2010
%I ACM
%K recommender, social-network
%P 1103--1104
%R 10.1145/1772690.1772825
%T SNDocRank: Document Ranking Based on Social Networks
%U http://dx.doi.org/10.1145/1772690.1772825
%X To improve the search results for socially-connect users, we propose a ranking framework, Social Network Document Rank (SNDocRank). This framework considers both document contents and the similarity between a searcher and document owners in a social network and uses a Multi-level Actor Similarity (MAS) algorithm to efficiently calculate user similarity in a social network. Our experiment results based on YouTube data show that compared with the tf-idf algorithm, the SNDocRank method returns more relevant documents of interest. Our findings suggest that in this framework, a searcher can improve search by joining larger social networks, having more friends, and connecting larger local communities in a social network.
%@ 978-1-60558-799-8
@inproceedings{citeulike:13839839,
abstract = {{To improve the search results for socially-connect users, we propose a ranking framework, Social Network Document Rank (SNDocRank). This framework considers both document contents and the similarity between a searcher and document owners in a social network and uses a Multi-level Actor Similarity (MAS) algorithm to efficiently calculate user similarity in a social network. Our experiment results based on YouTube data show that compared with the tf-idf algorithm, the SNDocRank method returns more relevant documents of interest. Our findings suggest that in this framework, a searcher can improve search by joining larger social networks, having more friends, and connecting larger local communities in a social network.}},
added-at = {2017-11-15T17:02:25.000+0100},
address = {New York, NY, USA},
author = {Gou, Liang and Chen, Hung H. and Kim, Jung H. and Zhang, Xiaolong L. and Giles, C. Lee},
biburl = {https://www.bibsonomy.org/bibtex/2578805125a8493fdb296a5d7ed924565/brusilovsky},
booktitle = {Proceedings of the 19th International Conference on World Wide Web},
citeulike-article-id = {13839839},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1772825},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/1772690.1772825},
doi = {10.1145/1772690.1772825},
interhash = {cab17ccb608047f435a17ac08eb2dc50},
intrahash = {578805125a8493fdb296a5d7ed924565},
isbn = {978-1-60558-799-8},
keywords = {recommender, social-network},
location = {Raleigh, North Carolina, USA},
pages = {1103--1104},
posted-at = {2015-11-17 04:40:50},
priority = {2},
publisher = {ACM},
series = {WWW '10},
timestamp = {2017-11-15T17:02:25.000+0100},
title = {{SNDocRank: Document Ranking Based on Social Networks}},
url = {http://dx.doi.org/10.1145/1772690.1772825},
year = 2010
}