Abstract

Objectives This study was conducted to investigate the LC/RC academic achievement and perceptions of students participating in TOEIC classes applying an artificial intelligence (AI)-based TOEIC program at S University.
 Methods For academic achievement analysis, the differences in the post-TOEIC scores of 64 and 74 students in the experimental and comparison groups, respectively, were analyzed using independent sample t-tests. To obtain more practical implications, the differences in pre and post TOEIC scores of the entire experimental group and the differences between two groups (upper & lower) which had been divided based on their pre-TOEIC scores were analyzed using paired sample t-tests. The interview data of 4 students concerning the AI-based classes were coded, classified, and categorized according to the qualitative analysis method.
 Results The TOEIC score of the experimental group was higher than that of the comparison group, but this finding lacked statistical significance. The TOEIC score of the experimental group, however, improved to a statistically significant level. The analysis according to the pre-TOEIC scores showed that the total and LC scores of the upper group improved, with LC showing a significant improvement. The total and both LC and RC scores of the lower group improved significantly. In the student perception analysis, a total of 111 meaningful statements were identified, and 3 categories (‘learning experience with an AI-based TOEIC program’, ‘class using an AI-based TOEIC program’, and ‘instructor’s role in promoting AI-based learning motivation’) and 7 sub-categories were derived.
 Conclusions Based on the results of the study, this study suggests utilizing AI-based TOEIC classes with Hyflex operation, implementing AI for customized LC learning for individual students, creating individual learning portfolios for RC improvement for the upper group, and for the AI program to provide detailed student-learning data to allow instructors to redesign classes effectively.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call