Interactive Recommender System Research Articles

Preference-based user rating correction process for interactive recommendation systems

In most of the recommendation systems, user rating is an important user activity that reflects their opinions. Once the users return their ratings about items the systems have suggested, the user ratings can be used to adjust the recommendation process.However, while rating the items users can make some mistakes (e.g., natural noises). As the recommendation systems receive more incorrect ratings, the performance of such systems may decrease. In this paper, we focus on an interactive recommendation system which can help users to correct their own ratings. Thereby, we propose a method to determine whether the ratings from users are consistent to their own preferences (represented as a set of dominant attribute values) or not and eventually to correct these ratings to improve recommendation. The proposed interactive recommendation system has been particularly applied to two user rating datasets (e.g., MovieLens and Netflix) and it has shown better recommendation performance (i.e., lower error ratings).

Personalized Recommendation in Interactive Visual Analysis of Stacked Graphs

We present a system which combines interactive visual analysis and recommender systems to support insight generation for the user. Our approach combines a stacked graph visualization with a content-based recommender algorithm, where promising views can be revealed to the user for further investigation. By exploiting both the current user navigational data and view properties, the system allows the user to focus on visual space in which she or he is interested. After testing with more than 30 users, we analyze the results and show that accurate user profiles can be generated based on user behavior and view property data.

User-selectable interactive recommendation system in mobile environment

Mobile devices need to provide more accurate and personalized information in a computing environment with a small screen and limited information retrieval functions. This paper presents a user-selectable recommendation system that reflects a user interest group by employing collaborative filtering as technique to provide useful information in a mobile environment. We form similar groups by simultaneously considering a user's information preferences and demographics. Then we reconstruct lists of a final recommendation based on what search results the similar demographic group has chosen. This is an optional filter for the search results. This means that we provide an interactive flexible recommendation list that considers a user's intent more actively, rather than unilaterally. We show the Mean Absolute Error result to evaluate the recommendation and finally show the realization of a prototype that is based on both the iPhone and Android phone environments.

SmallWorlds: Visualizing Social Recommendations

AbstractWe present SmallWorlds, a visual interactive graph‐based interface that allows users to specify, refine and build item‐preference profiles in a variety of domains. The interface facilitates expressions of taste through simple graph interactions and these preferences are used to compute personalized, fully transparent item recommendations for a target user. Predictions are based on a collaborative analysis of preference data from a user's direct peer group on a social network. We find that in addition to receiving transparent and accurate item recommendations, users also learn a wealth of information about the preferences of their peers through interaction with our visualization. Such information is not easily discoverable in traditional text based interfaces. A detailed analysis of our design choices for visual layout, interaction and prediction techniques is presented. Our evaluations discuss results from a user study in which SmallWorlds was deployed as an interactive recommender system on Facebook.

Fast computation of query relaxations for knowledge-based recommenders

“No matching product found” is an undesirable message for the user of an online product finder application or interactive recommender system. Query Relaxation is an approach to recovery from such retrieval failures and works by eliminating individual parts of the original query in order to find products that satisfy as many of the user's constraints as possible. In this paper, new techniques for the fast computation of “user-optimal” query relaxations are proposed. We show how the number of costly catalog queries can be minimized with the help of a query pre-processing approach, how we can compute relaxations that contain at least n items in the recommendation, and finally, how a recent conflict-detection algorithm can be applied for fast determination of preferred conflicts in interactive recovery scenarios.