A Feature-based Approach to Recommending Selections based on Past Preferences

The increasing availability of a large number of interactive multi-media information services means that users have a large and diverse collection of choices open to them. This diversity and choice may present navigation difficulties to users which can dissuade them from using such services. One method of assisting users to navigate through large collections is to use information filtering to extract only the information relevant to an end-user according to his/her long-term preferences. In this paper, we describe a mechanism to acquire a user's long-term preferences (user profile), and then show how the acquired profile may be used to recommend selections that may be of interest to the user. The profile is acquired on the basis of a user's habits using a Heuristic-Statistical approach, and is used to create selection indices which are then used during on-line interactions to recommend selections. Our mechanism has been incorporated into an experimental Video On Demand (VOD) service that is implemented using a client-server architecture. The profile acquisition component is incorporated into a VOD server on a multi-tasking machine, while the VOD user interface resides on a personal computer. Our mechanism for acquiring profiles and making recommendations has been quantitatively evaluated on the basis of data collected about movie preferences.

[1]  Donna K. Harman,et al.  Overview of the Second Text REtrieval Conference (TREC-2) , 1994, HLT.

[2]  Nicholas J. Belkin,et al.  Information filtering and information retrieval: two sides of the same coin? , 1992, CACM.

[3]  Shoshana Loeb,et al.  Architecting personalized delivery of multimedia information , 1992, CACM.

[4]  Steven J. Plimpton,et al.  Massively parallel methods for engineering and science problems , 1994, CACM.

[5]  Edward M. Housman,et al.  State of the Art in Selective Dissemination of Information , 1970, IEEE Transactions on Engineering Writing and Speech.

[6]  Douglas W. Oard,et al.  The State of the Art in Text Filtering , 1997, User Modeling and User-Adapted Interaction.

[7]  Kevin Crowston,et al.  How do experienced information lens users use rules? , 1989, CHI '89.

[8]  Gerard Salton,et al.  Improving retrieval performance by relevance feedback , 1997, J. Am. Soc. Inf. Sci..

[9]  Pattie Maes,et al.  Collaborative Interface Agents , 1994, AAAI.

[10]  Pattie Maes,et al.  Evolving agents for personalized information filtering , 1993, Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications.

[11]  Pattie Maes,et al.  Learning Interface Agents , 1993, AAAI.

[12]  Elaine Rich,et al.  User Modeling via Stereotypes , 1998, Cogn. Sci..

[13]  Robert B. Allen,et al.  User Models: Theory, Method, and Practice , 1990, Int. J. Man Mach. Stud..

[14]  Jennifer Chu-Carroll,et al.  Recognizing and Utilizing User Preferences in Collaborative Consultation Dialogues , 1994 .

[15]  Michael McGill,et al.  Introduction to Modern Information Retrieval , 1983 .

[16]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[17]  Susan T. Dumais,et al.  Personalized information delivery: an analysis of information filtering methods , 1992, CACM.

[18]  Judy Kay,et al.  The um toolkit for cooperative user modelling , 2005, User Modeling and User-Adapted Interaction.

[19]  Pattie Maes,et al.  Agents that reduce work and information overload , 1994, CACM.

[20]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[21]  Andrew Jennings,et al.  A Personal News Service Based on a User Model Neural Network , 1992 .

[22]  E. Kreyszig,et al.  Advanced Engineering Mathematics. , 1974 .