作者: Tony Cheng-Kui Huang , Chih-Hong Huang , Yung-Ting Chuang
DOI: 10.1016/J.TELE.2015.10.005
关键词:
摘要: This study proposes a model to detect the change in students' learning performance.This helps educators understand behaviors dynamic environments.Experiments are conducted with real-life datasets evaluate effectiveness of model. In recent years, as information technology has become more prevalent, management systems have arisen around e-learning and web-based platforms. As result, huge quantities data about process been recorded stored. Teachers can apply data-mining techniques mine performance. One such technique is association rule mining, which find correlations between student characteristics For instance, (Attendance=Middle)?(Gender=Male)?(Semester=Low) indicates that semester grade students at Low level if their gender Male attendance rate Middle, where Middle predetermined linguistic terms given by teachers. rely on rules formulate teaching strategies. However, these may be varied different semesters because or method The above used describe behavior during last semester, yet, within this changes (Attendance=Low)?(Gender=Female)?(Semester=Low). Without updating knowledge, teachers might adopt inappropriate strategies for who ways across semesters. study, we propose new mining discover performance basis rules. We experiments proposed