From The Theme
ONLINE MEDIA CONTENT
What if we could develop a truly fair, comprehensive and anonymous mechanism for assigning reputation ratings to self-published work online?
WHAT WE SET OUT TO DO
We set out to explore reputation systems, with a focus on the feasibility of algorithmic techniques that address the issues of reputation, trust, and anonymity in peer to peer (P2P) publishing and content sharing. We examined review-based rating systems for intellectual or artistic content, mechanisms to mitigate collusive behavior online, and improvements to ranking systems that help channel trust to reputable reviewers.
WHAT WE FOUND
Our exploration of reputation systems led to a variety of insights:
•We researched and developed incentive based ranking and recommendation mechanisms, as well as new models and algorithms for improving the collaborative filtering systems used in automated recommendation engines.
•We found that web search results can be improved with interactive systems such as those that provide relevance feedback.
•We found that articulating transaction costs improves the functionality of binary feedback reputation systems such as eBay, and reduces reputation issues like ballot stuffing and bad mouthing.
•Our experiments with the pricing & placement of advertising slots on a web page found that revenues from a “truthful auction,” which ranked ads in accordance with their bids, were equivalent with current, less transparent and less efficient auction methods.
•We found that webpage popularity is influenced by the age and quality of the page. At the same time, our randomized ranking approach succeeded in accelerating the popularity evolution of new webpages.
R. Bhattacharjee and A. Goel. Algorithms and Incentives for Robust Ranking. ACM-SIAM Symposium on Discrete Algorithms (SOAD) 2007.
R. Bhattacharjee and A. Goel. Avoiding ballot stufﬁng in eBay-like reputation systems. Third Workshop on Economics of Peer-to-Peer systems, Aug 2005.
G. Aggarwal, A. Goel, and R. Motwani. Truthful auctions for pricing search keywords. Proceedings of the seventh ACM conference on Electronic Commerce, June 2006.
PEOPLE BEHIND THE PROJECT
Ashish Goel is a Professor of Management Science and Engineering and (by courtesy) Computer Science at Stanford University. He received his PhD in Computer Science from Stanford in 1999, and was an Assistant Professor of Computer Science at the University of Southern California from 1999 to 2002. His research interests lie in the design, analysis, and applications of algorithms.
The Late Rajeev Motwani was a Professor of Computer Science at Stanford University, where he also served as the Director of Graduate Studies. He obtained his Ph.D. in Computer Science from Berkeley in 1988. His research spanned a diverse set of areas in computer science, including databases, data mining, and data privacy, web search and information retrieval, robotics, computational drug design, and theoretical computer science.