Experimental investigation of high performance cognitive and interactive text filtering
Douglas W. Oard, Nicholas DeClaris, Bonnie Jean Dorr, Christos Faloutsos, Gary Marchionini · 2002
Text filtering has become increasingly important as the volume of networked information has exploded in recent years. This paper reviews recent progress in that field and reports on the development of a testbed for experimental investigation of cognitive and interactive text selection based on a history of user evaluations. An interactive filtering system model is presented and a new cognitive filtering technique which the authors call the Gaussian User Model is described. Because development of analytic measures of text selection effectiveness has proven intractable, the authors have modified the Cornell SMART text retrieval system to create a flexible text filtering testbed for experimental determination of filtering effectiveness. The paper concludes with a description of the design of this testbed system.