Personalized Knowledge Acquisition through Interactive Data Analysis in E-learning System Zhongying Zhao Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China Graduate School of Chinese Academy of Sciences, Beijing, China Email: zy.zhao@sub.siat.ac.cn Shengzhong Feng 1 , Qingtian Zeng 2 , Jianping Fan 1 , and Xiaohong Zhang 1 1 Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China 2 College of Information Science and Engineering, Shandong University of Science and Technology, Qingdao, China Email: sz.feng@siat.ac.cn , qtzeng@sdust.edu.cn ,{jp.fan, xh.zhang}@siat.ac.cn Abstract—Personalized knowledge acquisition is very important for promoting learning efficiency within E- learning system. To achieve this, two key problems involved are acquiring user’s knowledge requirements and discovering the people that can meet the requirements. In this paper, we present two approaches to realize personalized knowledge acquisition. The first approach aims to mine what knowledge the student requires and to what degree. All the interactive logs, accumulated during question answering process, are taken into account to compute each student’s knowledge requirement. The second approach is to construct and analyze user network based on the interactive data, which aims to find potential contributors list. Each student’s potential contributors may satisfy his/her requirement timely and accurately. Then we design an experiment to implement the two approaches. In order to evaluate the performance of our approaches, we make an evaluation with the percentage of satisfying recommendations. The evaluation results show that our approaches can help each student acquire the knowledge that he/she requires efficiently. Index Terms—E-learning, knowledge acquisition, knowledge requirement, potential contributor I. INTRODUCTION Personalized support becomes even more important, when e-Learning takes place in open and dynamic learning and information networks [1, 2, 3]. Personalized knowledge acquisition, is one of the most important phases for realizing user-adaptive or personalized e- learning systems. It involves several aspects. The first is to acquire what knowledge the student requires. The second problem is to find who can provide the related knowledge to satisfy student’s requirement. Others include how to offer the knowledge, in what forms and what time. In this paper, we aim to solve the first two problems. Interactive Question Answering (QA) system, which can be seen as virtual seminar, has been embedded into an e-learning system to improve learning performance [4, 5, 6]. During this system, students communicate their knowledge in the form of posing questions, selecting questions to answer and browsing others’ questions and answers (Q&A). The e-learning system can store all these interactive logs into the data base in the form of question table, answer table and user table. All of these historical data contain a tremendous amount of information about the users’ requirements and relations. In this paper, we propose two approaches to achieve personalized knowledge acquisition. The first approach aims to mine what topics (what kind of knowledge) the user requires and to what degree. All his/her interactive logs, including posing question, answering questions and browsing answers, are taken into account to compute the knowledge requirement. This approach, however, does not imply whom a student can turn to when he/she has knowledge requirements. And the tightness of relations between students is also not reflected although it is very important for users to acquire knowledge. Thus, our second approach is to construct a user network for all the users in e-learning system. The user network describes each student’s potential contributors list and the relation strength, which can improve the personalized knowledge acquisition. Compared with others’ excellent research results, the work in this paper is a supplement to achieve personalized E-learning, especially in personalized knowledge acquisition. The remainder of the paper is organized as follows. In section 2, we discuss the related work. Section 3 describes the framework for personalized knowledge acquisition. Section 4 presents the approach for mining user’s knowledge requirement. The construction and analysis of the user network is addressed in section 5, which aims to find the potential contributors. Section 6 combines our two approaches to achieve personalized knowledge acquisition. To evaluate our approaches, we design the experiment and evaluation in section 7. Section 8 concludes the whole paper and discusses the future work. II. RELATED WORK JOURNAL OF COMPUTERS, VOL. 5, NO. 5, MAY 2010 709 © 2010 ACADEMY PUBLISHER doi:10.4304/jcp.5.5.709-716