Improving Digital Library Ranking with Expert Information

Open Access
Chen, Yuan-hsin
Graduate Program:
Information Sciences and Technology
Master of Science
Document Type:
Master Thesis
Date of Defense:
May 14, 2015
Committee Members:
  • C Lee Giles, Thesis Advisor
  • academic search engine
  • learning to rank
The purpose of this research is to investigate whether expert information can improve the ranking function of academic search engines. We chose CiteSeerX as the testbed which is a well-known academic paper search engine where the ranking function takes into consideration the number of citations and the similarity between the query and the paper. Therefore, papers with higher citations are easier to get higher positions in the ranking list. Thus, adding more features to the ranking function may reduce the bias of one or a few factors. Intuitively, if an author of a paper is an expert in the area, the paper should be more credible and also searchers should be more interested in. This research found that a document whose author is an expert has a higher probability to be clicked than a document which does not contain one. Furthermore, we included expert information as another feature of CiteSeerX’s ranking function. A supervised ranking approach that considers expert information was used. The evaluation shows that the two learned ranking functions perform better than CiteSeerX’s existing one.