Briefs

D-Lib Magazine (10/05) Vol. 11, No. 10; Custard, Myra; Sumner, Tamara

Myra Custard and Tamara Sumner of the University of Colorado at Boulder's Department of Computer Science outline a methodology to automate quality assessments of digital library resources and collections using machine-learning techniques.

Resource and collection "quality" is becoming an increasingly important topic for educational digital libraries. Computational models of quality and automated approaches for computing the quality of digital resources are necessary components of next generation cognitive tools aimed at supporting collection curators in making quality decisions. This research identifies and computes metrics for 16 quality indicators (e.g., cognitive authority, resource currency, cost, and advertising) and employs machine-learning techniques to classify resources into different quality bands based on these indicators.

In experiments, metadata currency was rated the single best quality indicator.

Here is the rest of the story.