Thursday 31 July, 14:00 - 15:30Chair: Barry Smyth
A Rule-Based Recommender System for Online Discussion Forums (page 12)Fabian Abel, Ig Ibert Bittencourt, Nicola Henze, Daniel Krause, and Julita Vassileva
In this paper we present a rule-based personalization framework for encapsulating and combining personalization algorithms known from adaptive hypermedia and recommender systems. We show how this personalization framework can be integrated into existing systems by example of the educational online board Comtella-D, which exploits the framework for recommending relevant discussions to the users. In our evaluations we compare different recommender strategies, investigate usage behavior over time, and show that a small amount of user data is sufficient to generate precise recommendations.
Locally Adaptive Neighborhood Selection for Collaborative Filtering Recommendations (page 22)Linas Baltrunas and Francesco Ricci
User-to-user similarity is a fundamental component of Collaborative Filtering (CF) recommender systems. In user-to-user similarity the ratings assigned by two users to a set of items are pairwise compared and averaged (correlation). In this paper we make user-to-user similarity adaptive, i.e., we dynamically change the computation depending on the profiles of the compared users and the target item whose rating prediction is sought. We propose to base the similarity between two users only on the subset of co-rated items which best describes the taste of the users with respect to the target item. These are the items which have the highest correlation with the target item. We have evaluated the proposed method using a range of error measures and showed that the proposed locally adaptive neighbor selection, via item selection, can significantly improve the recommendation accuracy compared to standard CF.
Concept-Based Document Recommendations for CiteSeer Authors (page 83)Kannan Chandrasekaran, Susan Gauch, Praveen Lakkaraju, and Hiep Phuc Luong
The information explosion in today's electronic world has created the need for information filtering techniques that help users filter out extraneous content to identify the right information they need to make important decisions. Recommender systems are one approach to this problem, based on presenting potential items of interest to a user rather than requiring the user to go looking for them. In this paper, we propose a recommender system that recommends research papers of potential interest to authors known to the CiteSeer database. For each author participating in the study, we create a user profile based on their previously published papers. Based on similarities between the user profile and profiles for documents in the collection, additional papers are recommended to the author. We introduce a novel way of representing the user profiles as trees of concepts and an algorithm for computing the similarity between the user profiles and document profiles using a tree-edit distance measure. Experiments with a group of volunteers show that our concept-based algorithm provides better recommendations than a traditional vector-space model based technique.