This paper studies people recommendations designed to help users find known, offline contacts and discover new friends on social networking sites. We evaluated four recommender algorithms in an enterprise social networking site using a personalized survey of 500 users and a field study of 3,000 users. We found all algorithms effective in expanding users' friend lists. Algorithms based on social network information were able to produce better-received recommendations and find more known contacts for users, while algorithms using similarity of user-created content were stronger in discovering new friends. We also collected qualitative feedback from our survey users and draw several meaningful design implications.
%0 Conference Paper
%1 citeulike:4545636
%A Chen, Jilin
%A Geyer, Werner
%A Dugan, Casey
%A Muller, Michael
%A Guy, Ido
%B Proceedings of the 27th international conference on Human factors in computing systems
%C New York, NY, USA
%D 2009
%I ACM
%K recommender social-network social-web
%P 201--210
%R 10.1145/1518701.1518735
%T Make new friends, but keep the old: recommending people on social networking sites
%U http://dx.doi.org/10.1145/1518701.1518735
%X This paper studies people recommendations designed to help users find known, offline contacts and discover new friends on social networking sites. We evaluated four recommender algorithms in an enterprise social networking site using a personalized survey of 500 users and a field study of 3,000 users. We found all algorithms effective in expanding users' friend lists. Algorithms based on social network information were able to produce better-received recommendations and find more known contacts for users, while algorithms using similarity of user-created content were stronger in discovering new friends. We also collected qualitative feedback from our survey users and draw several meaningful design implications.
%@ 978-1-60558-246-7
@inproceedings{citeulike:4545636,
abstract = {{This paper studies people recommendations designed to help users find known, offline contacts and discover new friends on social networking sites. We evaluated four recommender algorithms in an enterprise social networking site using a personalized survey of 500 users and a field study of 3,000 users. We found all algorithms effective in expanding users' friend lists. Algorithms based on social network information were able to produce better-received recommendations and find more known contacts for users, while algorithms using similarity of user-created content were stronger in discovering new friends. We also collected qualitative feedback from our survey users and draw several meaningful design implications.}},
added-at = {2018-03-19T12:24:51.000+0100},
address = {New York, NY, USA},
author = {Chen, Jilin and Geyer, Werner and Dugan, Casey and Muller, Michael and Guy, Ido},
biburl = {https://www.bibsonomy.org/bibtex/2df70bd2fa9bf06a8b21f0be7f725f98c/aho},
booktitle = {Proceedings of the 27th international conference on Human factors in computing systems},
citeulike-article-id = {4545636},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1518701.1518735},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/1518701.1518735},
doi = {10.1145/1518701.1518735},
interhash = {7360b3425b853facefbe401b191f9647},
intrahash = {df70bd2fa9bf06a8b21f0be7f725f98c},
isbn = {978-1-60558-246-7},
keywords = {recommender social-network social-web},
location = {Boston, MA, USA},
pages = {201--210},
posted-at = {2010-01-29 17:10:23},
priority = {2},
publisher = {ACM},
series = {CHI '09},
timestamp = {2018-03-19T12:24:51.000+0100},
title = {{Make new friends, but keep the old: recommending people on social networking sites}},
url = {http://dx.doi.org/10.1145/1518701.1518735},
year = 2009
}