Personalized recommendation of social software items based on social relations

ABSTRACT

We study personalized recommendation of social software items, including bookmarked web-pages, blog entries, and communities. We focus on recommendations that are derived from the user's social network. Social network information is collected and aggregated across different data sources within our organization. At the core of our research is a comparison between recommendations that are based on the user's familiarity network and his/her similarity network. We also examine the effect of adding explanations to each recommended item that show related people and their relationship to the user and to the item. Evaluation, based on an extensive user survey with 290 participants and a field study including 90 users, indicates superiority of the familiarity network as a basis for recommendations. In addition, an important instant effect of explanations is found - interest rate in recommended items increases when explanations are provided.

References

1. Amitay, E., Carmel, D., Har'el, N., Soffer, A., Golbandi, N., Ofek-Koifman, S.,&Yogev, S. 2009. Social search and discovery using a unified approach. Proc. HT'09, 199--208.
2. Arguello, J., Elsas, J., Callan, J.,&Carbonell J. 2008. Document representation and query expansion models for blog recommendation. Proc. ICWSM'08.
3. Bonhard, P.&Sasse, M. A. 2006. 'Knowing me, knowing you' -- Using profiles and social networking to improve recommender systems. BT Technology Journal 24, 3 (Jul. 2006), 84--98.
4. Claypool, M., Le, P., Wased, M.,&Brown, D. 2001. Implicit interest indicators. Proc. IUI '01, 33--40.
5. Dugan, C., Muller, M., Millen, D.R., Geyer, W., Brownholtz, B.,&Moore, M. 2007. The dogear game: a social bookmark recommender system. Proc. GROUP'07, 387--390.
6. Geyer, W., Dugan, C., Millen, D., Muller, M.,&Freyne, J. 2008. Recommending topics for self-descriptions in online user profiles. Proc. RecSys'08, 59--66.
7. Goldberg, D., Nichols, D., Oki, B. M., and Terry, D. 1992. Using collaborative filtering to weave an information tapestry. Commun. ACM 35, 12 (Dec. 1992), 61--70.
8. Groh, G., and Ehmig, C. 2007. Recommendations in Taste Related Domains: Collaborative Filtering vs. Social Filtering. Proc. GROUP'07, 127--136.
9. Guy, I., Jacovi, M., Meshulam, N., Ronen, I.,&Shahar, E. 2008. Public vs. private -- comparing public social network information with email. Proc. CSCW'08, 393--402.
10. Guy, I., Jacovi, M., Shahar, E., Meshulam, N., Soroka, V.,&Farrell, S. 2008. Harvesting with SONAR: the value aggregating social network information. Proc. CHI'08, 1017--1026.
11. Guy I., Ronen I.,&Wilcox E. 2009. Do you know? recommending people to invite into your social network. Proc. IUI'09, 77--86.
12. Herlocker, J. L., Konstan, J.A.,&Riedl, J. 2000. Explaining collaborative filtering recommendations. Proc. CSCW'00, 241--250.
13. IBM Social Software for Business -- Lotus Connections: http://www-01.ibm.com/software/lotus/products/connections/.
14. Jackson, A., Yates, J.,&Orlikowski, W. 2007. Corporate blogging: building community through persistent digital talk. Proc. HICSS'07, 80.
15. Java, A., Kolari, P., Finin, T., Joshi, A.,&Oates, T. 2007. Feeds that matter: a study of Bloglines subscriptions. Proc. ICWSM'07.
16. Kautz, H., Selman, B.,&Shah, M. 1997. ReferralWeb: Combining social networks and collaborative filtering. Commun. ACM 40, 3 (Mar. 1997) 63--65.
17. Lerman, K. 2007. Social networks and social information filtering on Digg. Proc. ICWSM'07.
18. McSherry, D. Explanation in recommender systems. 2005. Artif. Intell. Rev. 24, 2 (Oct. 2005), 179--197.
19. Millen, D.R., Feinberg, J.,&Kerr, B. 2006. Dogear: Social bookmarking in the enterprise. Proc. CHI'06, 111--120.
20. Offical Digg Blog: http://blog.digg.com/?p=127.
21. Official Facebook Blog: http://blog.facebook.com/blog.php?post=2207967130.
22. Official FriendFeed Blog: http://blog.friendfeed.com/2008/06/friendfeed-adds-personalized.html.
23. Schein, A. I., Popescul, A., Ungar, L. H.,&Pennock, D. M. 2002. Methods and metrics for cold-start recommendations. Proc. SIGIR'02, 253--260.
24. Seth, A.,&Zhang, J. 2008. A social network based approach to personalized recommendation of participatory media content. Proc. ICWSM'08.
25. Sinha, R.&Swearingen, K. 2001. Comparing recommendations made by online systems and friends. Proc. DELOS-NSF Workshop on Personalization and Recommender Systems in Digital Libraries.
26. Spertus, E., Sahami, M.,&Buyukkokten, O. 2005. Evaluating similarity measures: a large-scale study in the Orkut social network. Proc. SIGKDD'05, 678--684.
27. Tepper, M. 2003. The rise of social software. netWorker 7, 3 (Sep. 2003), 18--23.
28. Tintarev, N.&Masthoff, J. 2007. A Survey of explanations in recommender systems. Proc. ICDEW'07, 801--810.
29. Vatturi, P. K., Geyer, W., Dugan, C., Muller, M.,&Brownholtz, B. 2008. Tag-based filtering for personalized bookmark recommendations. Proc. CIKM'08, 1395--1396.
30. Wasserman, S.,&Faust, K. 1994. Social Network Analysis.

Index Terms

• Human-centered computing

  • Collaborative and social computing

• Information systems

  • Information retrieval

    • Retrieval tasks and goals

      • Document filtering

      • Information extraction