Dynamics of collaborative document rating systems

ABSTRACT

The rise of social media sites, such as blogs, wikis, Digg and Flickr among others, underscores a transformation of the Web to a participatory medium in which users are actively creating, evaluating and distributing information. The social news aggregator Digg allows users to submit links to and vote on news stories. Like other social media sites, Digg also allows users to designate others as "friends" and easily track friends' activities: what new stories they submitted, commented on or liked. Each day Digg selects a handful of stories to feature on its front page. Rather than rely on the opinion of a few editors, Digg aggregates opinions of thousands of its users to decide which stories to promote to the front page. We construct a mathematical model to study how collaborative rating and promotion of news stories emerges from independent decisions made by many users. The model takes into account user behavior: e.g., whether they read stories on the front page or through the Friends interface. Solutions of the model qualitatively reproduce the observed dynamics of votes received by actual stories on Digg.

Digg also ranks users according to how successful they are in getting their stories promoted to the front page. We create a model that describes how a user's rank changes in time as he gets more stories to the front page and becomes more influential in the community. We find qualitative agreement between predictions of the model and the evolution of rank for Digg users.

The Digg model of allowing users to collectively evaluate how interesting the news stories are can be generalized to collaborative evaluation of the quality of information. Mathematical analysis can be used as a tool to explore different voting methods to select the most effective one before the method is ever implemented in a real system.

REFERENCES

• 1: E. Adar, L. Zhang, L. A. Adamic, and R. M. Lukose. Implicit structure and the dynamics of blogspace. In Workshop on the Weblogging Ecosystem, 13th International World Wide Web Conference, 2004.
• 2: A. Dieberger , P. Dourish , K. Höök , P. Resnick , A. Wexelblat, Social navigation: techniques for building more usable systems, interactions, v.7 n.6, p.36-45, Nov./Dec. 2000 [doi>10.1145/352580.352587]
• 3: Henry Kautz , Bart Selman , Mehul Shah, Referral Web: combining social networks and collaborative filtering, Communications of the ACM, v.40 n.3, p.63-65, March 1997 [doi>10.1145/245108.245123]
• 4: Joseph A. Konstan , Bradley N. Miller , David Maltz , Jonathan L. Herlocker , Lee R. Gordon , John Riedl, GroupLens: applying collaborative filtering to Usenet news, Communications of the ACM, v.40 n.3, p.77-87, March 1997 [doi>10.1145/245108.245126]
• 5: K. Lerman. Social networks and social information filtering on digg. In Proc. of International Conference on Weblogs and Social Media (ICWSM-07) , 2007.
• 6: Kristina Lerman , Chris Jones , Aram Galstyan , Maja J Mataríc, Analysis of Dynamic Task Allocation in Multi-Robot Systems, International Journal of Robotics Research, v.25 n.3, p.225-241, March 2006 [doi>10.1177/0278364906063426]
• 7: K. Lerman and Laurie Jones. Social browsing on flickr. In Proc. of International Conference on Weblogs and Social Media (ICWSM-07), 2007.
• 8: K. Lerman, A. Martinoli, and A. Galstyan. A review of probabilistic macroscopic models for swarm robotic systems. In Sahin E. and Spears W., editors, Swarm Robotics Workshop: State-of-the-art Survey, number 3342 in LNCS, pages 143{152. Springer-Verlag, Berlin Heidelberg, 2005.
• 9: A. Martinoli, K. Easton, and W. Agassounon. Modeling of swarm robotic systems: A case study in collaborative distributed manipulation. Int. Journal of Robotics Research, 23(4):415{436, 2004.
• 10: P. Mika. Ontologies are us: A unified model of social networks and semantics. In International Semantic Web Conference (ISWC-05) , 2005.
• 11: Saverio Perugini , Marcos André Gonçalves , Edward A. Fox, Recommender Systems Research: A Connection-Centric Survey, Journal of Intelligent Information Systems, v.23 n.2, p.107-143, September 2004 [doi>10.1023/B:JIIS.0000039532.05533.99]
• 12: K. Rose. talk presented at the Web2.0 Conference, November 10 2006.
• 13: M.J. Salganik, P.S. Dodds, and D.J. Watts. Experimental study of inequality and unpredictability in an artificial cultural market. Science, 311:854, 2006.
• 14: J. Warren and J. Jurgensen. The wizards of buzz. Wall Street Journal online, Feb 2007.
• 15: F. Wu and B.A. Huberman. Novelty and collective attention. Technical report, Information Dynamics Laboratory, HP Labs, 2007.

INDEX TERMS

Keywords:
collaborative rating, mathematical analysis, news aggregation, social networks