Session: Innovative Preference Expressions and Usage Assessments
Chair: Markus Zanker
Date: Monday, September 27, 17:30-19:00
- Global budgets for local recommendations
by Thomas Sandholm, Hang Ung, Christina Aperjis, Bernardo A. Huberman
We present the design, implementation and evaluation of a new geotagging service, Gloe, that makes it easy to find, rate and recommend arbitrary on-line content in a mobile setting. The service automates the content search process by taking advantage of geographic and social context, while using crowdsourced expertise to present a personalized feed of targeted information ranked by a novel geo-aware rating and incentive mechanism.
Users rate the relevance of recommendations for particular locations using a limited, global voting budget. This budget is, in turn, increased by accurately predicting local content popularity. One of the key goals of our mechanism is to encourage ratings, and in an evaluation of the live system we found that the rating to click ratio was 107 times higher than the ratio for videos on YouTube, 34 times higher than the ratio for applications on the Android Market, and 3 times higher than the ratio for Web pages on Digg.
To investigate whether our mechanism also had qualitative effects on the ratings we conducted a number of experiments on Amazon Mechanical Turk, with 500 users, comparing our mechanism to the de-facto 5-star ratings commonly in use on the Web. Our results show that budgets improved the ranking and incentives improved the aggregate rating of a series of location-dependent Web pages.
- Aggregating preference graphs for collaborative rating prediction
by Maunendra Sankar Desarkar, Sudeshna Sarkar, Pabitra Mitra
Collaborative filtering is a widely used technique for rating prediction in recommender systems. Memory based collaborative filtering algorithms assign weights to the users to capture similarities between them. The weighted average of similar users’ ratings for the test item is output as prediction. We propose a memory based algorithm that is markedly different from the existing approaches. We use preference relations instead of absolute ratings for similarity calculations, as preference relations between items are generally more consistent than ratings across like-minded users. Each user’s ratings are viewed as a preference graph. Similarity weights are learned using an iterative method motivated by online learning. These weights are used to create an aggregate preference graph. Ratings are inferred to maximally agree with this aggregate graph. The use of preference relations allows the rating of an item to be influenced by other items, which is not the case in the weighted-average approaches of the existing techniques. This is very effective when the data is sparse, specially for the items rated by few users. Our experiments show that the our method outperforms other methods in the sparse regions. However, for dense regions, sometimes our results are comparable to the competing approaches, and sometimes worse.
- Eye-tracking product recommenders’ usage
by Sylvain Castagnos, Nicolas Jones, Pearl Pu
Recommender systems have emerged as an effective decision tool to help users more easily and quickly find products that they prefer, especially in e-commerce environments. However, few studies have tried to understand how this technology has influenced the way users search for products and make purchase decisions. Our current research aims at examining the impact of recommenders by understanding how recommendation tools integrate the classical economic schemes and how they modify product search patterns. We report our work in employing an eye tracking system and collecting users’ interaction behaviors as they browsed and selected products to buy from an online product retail website offering over 3,500 items. This in-depth user study has enabled us to collect over 48,000 fixation data points and 7,720 areas of interest from eighteen users, each spending more than one hour on our site. Our study shows that while users still use traditional product search tools to examine alternatives, recommenders definitely provide users with new opportunities in their decision process. More specifically, users actively click and gaze at products recommended to them, up to 40% of the time. In addition, recommendation areas are highly attractive, drawing users to add 50% more items to their baskets as a traditional tool does. Observing that users consult the recommendation area more as they are close to the end of their search process, it seems that recommenders enhance users’ decision confidence by satisfying their need for diversity. Based on these results, we derive several interaction design guidelines that can significantly improve users’ satisfaction and perception of product recommenders.
RecSys 2010 (Barcelona)
Sponsors and Benefactors
 |
 |
 |
 |
 |
 |
 |
 |