Access Type

Open Access Thesis

Date of Award

January 2015

Degree Type


Degree Name



Computer Science

First Advisor

Weisong Shi


There are massive research papers published from various of disciplines every year, and people who are engaged in scientific research usually have to spend a large amount of time on searching and finding the papers that they are interested in.

In this thesis, we illustrated a unique personalized literature recommender system (PLUS) which was proposed to predict users' personal research interests and recommend the latest papers to them as much as possible. The system shows advantages in four aspects: (1) it takes multiple sources that could reflect a user's personal research interest as the input; (2) it prevents the recommendations from going outdated due to the timely update to the user's interest and the Resource Pool; (3) it is targeted to recommend the latest papers to the users; and (4) it is using a comprehensive survey to evaluate users' satisfaction to the system, which is more approaching users' real interests. The experimental results showed that PLUS was capable of discovering the papers that users are indeed interested, and the time that the users have consumed on searching papers was reduced significantly with the help of this recommender system.