A Machine Learning Approach to Reducing the Work of Experts in Article Selection from Database: A Case Study for Regulatory Relations of S. cerevisiae Genes in MEDLINE

Shin-ichi Usuzaka[1] (shin@ib.sci.yamaguchi-u.ac.jp)
Kim Lan Sim[2] (klsim@ims.u-tokyo.ac.jp)
Miyako Tanaka[3] (miyako@ube-k.ac.jp)
Hiroshi Matsuno[1] (matsuno@sci.yamaguchi-u.ac.jp)
Satoru Miyano[2] (miyano@ims.u-tokyo.ac.jp)

[1] Faculty of Science, Yamaguchi University
1677-1 Yoshida, Yamaguchi 753-8512, Japan
[2] Human Genome Center, Institute of Medical Science, University of Tokyo
4-6-1, Shirokanedai, Minatoku 108-8639, Japan
[3] Department of Business Adminstration, Ube National College of Technology
2557, Tokiwadai, Ube 755-8555, Japan

Abstract

We consider the problem of selecting the articles of experts' interest from a literature database with the assistance of a machine learning system. For this purpose, we propose the rough reading strategy which combines the experts' knowledge with the machine learning system. For the articles converted through the rough reading strategy, we employ the learning system BONSAI and apply it for discovering rules which may reduce the work of experts in selecting the articles. Furthermore, we devise an algorithm which iterates the above procedure until almost all records of experts' interest are selected. Experimental results by using the articles from Cell show that almost all records of experts' interest are selected while reducing the works of experts drastically.

[ Full-text PDF | Table of Contents ]