Knowledge tracing (KT) models are a popular approach for predicting students' future performance at practice problems using their prior attempts. Though many innovations have been made in KT, most models including the state-of-the-art Deep KT (DKT) mainly leverage each student's response either as correct or incorrect, ignoring its content. In…

Personalized education systems recommend learning contents to students based on their capacity to accelerate their learning. This paper proposes a personalized exercise recommendation system for online self-directed learning. We first improve the performance of knowledge tracing models. Existing deep knowledge tracing models, such as Dynamic…

This paper reports research on student produced screencasts to support learning. Participants in a Mathematics for Teachers course were asked to create and peer critique screencasts to explain concepts (year 4 to 9 level). They were also asked about their experience with screencasting and its impact on their own teaching and learning. This paper…

It has been reported (Aagaard & Skidmore, 2004; Sikorski et al., 2002) that only a minority of college students actually read the course textbook in preparation for examinations. Although professors widely lament students' propensity to ignore the carefully chosen textbooks, research specifically investigating why this phenomenon occurs is…

A study investigated the composing process to examine why different types of instruction have different effects on composing products. The study contrasted three treatments: (1) presenting students with models (the traditional method); (2) the general procedures approach stressing freethinking process; and (3) a method stressing task-specific…

Library use instruction designed specifically for limited-English-proficient (LEP) students is discussed briefly and library skill activities used with this population at Union County College (New Jersey) are described. It is noted that many students from other countries have had little or no exposure to libraries because of either limited…