UNCONSCIOUS CONTRIBUTIONS Applying a connectionist model to design knowledge exchange

The distributed cognition approach, and by extension the domain of social intelligence design, attempts to integrate three until recently separate realms: mind, society, and matter. The field offers a heterogeneous collection of ideas, observations, and case studies, yet lacks a solid, coherent theoretical framework for building models of concrete systems and processes. Despite the intrinsic complexity of integrating individual, social and technologically-supported intelligence, the paper proposes a relatively simple "connectionist" framework for conceptualizing a distributed cognitive system. This framework represents shared information sources (documents) as nodes connected by links or associations of variable strength. The link strength increases interactively with the number of “co-activations” or co-occurrences of documents in the patterns of their usage. This connectionist learning procedure captures the implicit knowledge of its community of users and uses it to help them find relevant information, thus supporting an unconscious form of exchange. The principles are illustrated by an envisaged application to a concrete problem domain: the dynamic sharing of design knowledge among a multitude of architects by means of a database of associatively connected building projects.

[1]  P. Berger,et al.  The Social Construction of Reality , 1966 .

[2]  John Riedl,et al.  An algorithmic framework for performing collaborative filtering , 1999, SIGIR '99.

[3]  Mathias Géry,et al.  Evaluation of web usage mining approaches for user's next request prediction , 2003, WIDM '03.

[4]  B. Martens,et al.  ICT REVISITED - FROM INFORMATION & COMMUNICATION TO INTEGRATING CURRICULA? , 2004 .

[5]  Roger C. Schank,et al.  Dynamic memory - a theory of reminding and learning in computers and people , 1983 .

[6]  James E. Pitkow,et al.  In Search of Reliable Usage Data on the WWW , 1997, Comput. Networks.

[7]  Umeshwar Dayal,et al.  From User Access Patterns to Dynamic Hypertext Linking , 1996, Comput. Networks.

[8]  V. Rao Vemuri,et al.  Information filtering via hill climbing, wordnet, and index patterns , 1997, Inf. Process. Manag..

[9]  Johan Bollen.  Group User Models for Personalized Hyperlink Recommendations , 2000, AH.

[10]  Christopher K. Riesbeck,et al.  Inside Case-Based Reasoning , 1989 .

[11]  Margaret H. Dunham,et al.  Efficient mining of traversal patterns , 2001, Data Knowl. Eng..

[12]  Martin G. Helander,et al.  Hypertext and its Implications for the Internet , 1997 .

[13]  Johan Bollen,et al.  Adaptive networks of smart objects , 2002, Proceedings. International Conference on Parallel Processing Workshop.

[14]  Vincent Bouthors,et al.  Pharos, a Collaborative Infrastructure for Web Knowledge Sharing , 1999, ECDL.

[15]  Ann Heylighen,et al.  DYNAMO: A Dynamic Architectural Memory On-line , 2000, J. Educ. Technol. Soc..

[16]  Peter Lund,et al.  Providing a networked future for interpersonal information retrieval: InfoVine and user modelling , 1998, Interact. Comput..

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

[18]  Pattie Maes,et al.  Social information filtering: algorithms for automating “word of mouth” , 1995, CHI '95.

[19]  Paul P. Maglio,et al.  On Distinguishing Epistemic from Pragmatic Action , 1994, Cogn. Sci..

[20]  Tao Luo,et al.  Effective personalization based on association rule discovery from web usage data , 2001, WIDM '01.

[21]  Johan Bollen,et al.  An Adaptive Systems Approach to the Implementation and Evaluation of Digital Library Recommendation Systems , 2000, ECDL.

[22]  Mark Levene,et al.  A Probabilistic Approach to Navigation in Hypertext , 1999, Inf. Sci..

[23]  A. Clark.  Being There: Putting Brain, Body, and World Together Again , 1996 .

[24]  David M. Nichols,et al.  Browsing is a collaborative process , 1997, Inf. Process. Manag..

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

[26]  Francis Heylighen,et al.  Collective Intelligence and its Implementation on the Web: Algorithms to Develop a Collective Mental Map , 1999, Comput. Math. Organ. Theory.

[27]  Tom Ziemke,et al.  Social cognition, artefacts, and stigmergy: A comparative analysis of theoretical frameworks for the understanding of artefact-mediated collaborative activity , 2001, Cognitive Systems Research.

[28]  Johan Bollen,et al.  Hebbian algorithms for a digital library recommendation system , 2002, Proceedings. International Conference on Parallel Processing Workshop.

[29]  B. Buttenfield,et al.  Information and Institutional Change: The Case of Digital Libraries , 2003 .

[30]  Ahmad M. Ahmad Wasfi.  Collecting user access patterns for building user profiles and collaborative filtering , 1998, IUI '99.

[31]  Maguelonne Teisseire,et al.  Using data mining techniques on Web access logs to dynamically improve hypertext structure , 1999, LINK.

[32]  Hsinchun Chen,et al.  Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering , 2004, TOIS.

[33]  Antonio Picariello,et al.  Web personalization based on static information and dynamic user behavior , 2004, WIDM '04.

[34]  F. Heylighen,et al.  The Emergence of Distributed Cognition : a conceptual framework , 2004 .

[35]  Jaideep Srivastava,et al.  Automatic personalization based on Web usage mining , 2000, CACM.