Towards Intelligent and Adaptive Digital Library Services

In this paper, we introduced a 3-Layer digital library architecture that facilitates intelligent and adaptive digital library services. We aimed at integrating DL contents with domain-ontology, user-profile and usage-pattern by means of intelligent algorithms and techniques. On top of an open-source digital library system, we developed required modules to capture and manipulate necessary data with the help of efficient techniques such as ontology-driven topic inference, collaborative filtering, single exponential smoothing, etc. We verified that our approach is capable of enhancing and adapting user profile dynamically with the help of ontology-driven topic inference and usage-pattern analysis. Usage pattern and content -based collaborative-filtering techniques are used in developing adaptive recommendation service. We also proposed a User Interest-Drift algorithm based on single exponential smoothing techniques. Our preliminary experimental results and exploratory analyses show that our approach has created positive user experience in a small digital library environment. Large scale deployment of the proposed digital library system along with further refinement of algorithms is also planned.

[1]  Ian H. Witten,et al.  How to Build a Digital Library , 2002 .

[2]  Yan Yang,et al.  Interest-based Recommendation in Digital Library , 2005 .

[3]  Akito Monden,et al.  Javawock: A Java Class Recommender System Based on Collaborative Filtering , 2005, SEKE.

[4]  Carl Gutwin,et al.  KEA: practical automatic keyphrase extraction , 1999, DL '99.

[5]  Christopher Olston,et al.  ScentTrails: Integrating browsing and searching on the Web , 2003, TCHI.

[6]  Xue Li,et al.  Time weight collaborative filtering , 2005, CIKM '05.

[7]  Stuart E. Middleton,et al.  Capturing knowledge of user preferences: ontologies in recommender systems , 2001, K-CAP '01.

[8]  Gobinda G. Chowdhury,et al.  Introduction to Digital Libraries , 2002 .

[9]  Hinrich Schütze,et al.  Personalized search , 2002, CACM.

[10]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[11]  Jane Hunter,et al.  Digital Libraries: Achievements, Challenges and Opportunities, 9th International Conference on Asian Digital Libraries, ICADL 2006, Kyoto, Japan, November 27-30, 2006, Proceedings , 2006, International Conference on Asian Digital Libraries.

[12]  Peter Brusilovsky,et al.  Methods and techniques of adaptive hypermedia , 1996, User Modeling and User-Adapted Interaction.

[13]  I-En Liao,et al.  A Personal Ontology Model for Library Recommendation System , 2006, ICADL.

[14]  Susan T. Dumais,et al.  Optimizing search by showing results in context , 2001, CHI.

[15]  Peter Haase,et al.  Management of dynamic knowledge , 2005, J. Knowl. Manag..

[16]  Bradley N. Miller,et al.  GroupLens: applying collaborative filtering to Usenet news , 1997, CACM.

[17]  Naren Ramakrishnan,et al.  Personalizing Web sites with mixed-initiative interaction , 2003 .

[18]  Gary Marchionini,et al.  Information Seeking in Electronic Environments , 1995 .

[19]  Manfred A. Jeusfeld,et al.  Beyond information searching and browsing: acquiring knowledge from digital libraries , 2005, Inf. Process. Manag..

[20]  Susan Gauch,et al.  Improving Ontology-Based User Profiles , 2004, RIAO.

[21]  Eric Horvitz,et al.  Collaborative Filtering by Personality Diagnosis: A Hybrid Memory and Model-Based Approach , 2000, UAI.

[22]  Aimilia Tzanavari,et al.  Combining Collaborative and Content-Based Filtering Using Conceptual Graphs , 2003, Modelling with Words.

[23]  Hsinchun Chen,et al.  A graph-based recommender system for digital library , 2002, JCDL '02.

[24]  Fabio Crestani,et al.  Application of Spreading Activation Techniques in Information Retrieval , 1997, Artificial Intelligence Review.

[25]  Howard Besser,et al.  The Making of America II Testbed Project: A Digital Library Service Model. , 1999 .

[26]  Peter Brusilovsky,et al.  Adaptive Hypermedia , 2001, User Modeling and User-Adapted Interaction.