Exploring the Questionnaire Data of the Reading Behavior of College Students

• Main Authors: Wang-Ching Hung, 洪婉菁
• Other Authors: Don-Lin Yang
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/95670655678933489799

碩士 === 逢甲大學 === 資訊工程所 === 98 === Questionnaire survey is a method that helps us understand the thinking or comments from a sampled set of people. Traditionally, we always use statistics to analyze the collected questionnaire data. However there exist some problems, for example, we can''t use statistical method to process multiple choices data and analyze multidimensional questions. So we propose a systematic framework to solve the problem of using statistics to analyze questionnaire data. In the systematic framework, we utilize association rule mining of data mining technology to analyze the data. Because the result of association rule mining has too many rules, their applications are limited and not easy to use. We transform the presentation of resulted rules into tree structure to make users understand and use them more easily. As a result, users can modify the designed questionnaire to make survey hit the target of respondents’ thinking or habit and find out more useful information next time. We use the questionnaire data of the reading behavior of college students in our proposed framework. Because the questionnaire data include multiple choices, we exploit association rule mining with multiple dimensions to find out the factor of affecting students’ reading motivation and habit. The results are shown in a tree structure for easy understanding and better explanation.