Questions and Answers Database Construction for Adaptive Online IRT Testing Systems: Analysis Course and Linear Algebra Course

Information Engineering Express

2019

Self Cite

To find key factors not to drop out using learning analytics, we have added accumulated data such as the number of successes in learning check testing, the number of attendances to follow-up program classes, and etc., in addition to learning check testing ability scores performed at each lecture. Then, we have found key factors strongly related to the students at risk. They are the following. 1) Badly failed students (score range is 0-39 in the term ex-amination) tend to be absent for the regular classes and fail in learning check testing even if they attended, and they are very reluctant to attend follow-up program classes. 2) Success-ful students (score range is 60-100 in the term examination) attend classes and obtain good scores in every learning check testing. 3) Failed students but not so badly (score range is 40-59 in the term examination) reveal both sides of features appeared in score range of 0-39 and score range of 60-100. Therefore, it is crucial to attend lectures in order not to drop out. Students who failed in learning check testing more than half out of all testing times almost absolutely failed in the term examination, which could cause the drop out. Also, students who were successful to learning check testing more than two third out of all testing times took better score in the term examination.

Section: Introductionmentioning

confidence: 99%

Key Factor Not to Drop Out is to Attend Lectures

Information Engineering Express

2019

Self Cite

“…In such systems, we included learning check testing (LCT) for every class to measure student comprehension of lectures. The system has been successfully operating (see [16], [17]), and some computational results have been reported [19]. In addition, other relevant aspects have been investigated (see [18], [20], [21], [22], [26], [30]).…”

Section: Introductionmentioning

confidence: 99%

Prediction of Success or Failure for Examination using Nearest Neighbor Method to the Trend of Weekly Online Testing

International Journal of Learning Technologies and Learning Environments

2019

Self Cite

Using trends of estimated abilities in terms of item response theory for online testing, we can predict success/failure for term-end examinations for each student at early stages in courses. We applied the newly developed nearest neighbor method for determining the similarity of learning skills in the trends of estimated abilities, resulting in better prediction accuracy for success or failure. This paper shows that the use of the learning analytics incorporating trends for abilities is effective. ROC curve and recall precision curve are also utilized in the proposed method.

“…In such systems, we included the learning check testing, the LCT, for every class to check if students comprehend the contents of lectures or not. The system has been successfully operating (see [7], [8]), and some computational results were reported (see [10]). In addition, other relevant cases were well investigated (see [9], [11], [12], [13], [18], [21]).…”

Section: Introductionmentioning

confidence: 99%

Relationship Between Testing Time and Score in CBT

International Journal of Learning Technologies and Learning Environments

2019

Self Cite

By looking at the relationships between the numbers of correct answers and the time durations that students spend in taking tests, we have found that there are typical three patterns. The patterns of the time durations spent in taking the test to each number of correct answers depends on the difficulties of the questions. To easy problems to solve, some smart students can use less time to solve the problems and students with low academic ability need much time to solve. To moderate problems to solve, every student requires the similar time duration to solve the problems. To difficult problems to solve, many students tend to use full time to the pre-specified time duration, but some students with low ability may give up tackling the problem soon.