Machine learning with task-technology fit theory factors for predicting students' adoption in video-based learning

Nowadays, various innovative educational and instructional tools have been created to deliver learning material including video content. One of the important issues with video-based learning is to devise effective teaching strategies to ensure higher level of learning can be achieved by the students. Getting insight and predicting the students’ video-based learning adoption will help the educators. Thus, this study aims to examine the potential of using machine learning prediction models on video-based learning adoption in higher education institutions. Five machine learning algorithms were used to be empirically compared namely generalized linear model (GLM), random forest (RF), decision tree (DT), gradient boosted tree (GBT), and support vector machine (SVM). The performance of each machine learning algorithm in predicting the students’ learning adoption with video-based learning has been observed based on the attributes of task-technology fit theory. The findings indicated that the task-technology fit is useful in helping the machine learning algorithm to achieve high accuracy in the prediction of video-based learning adoption. The GBT is the best outperforming algorithm, followed with RF and SVM. This paper presents a fundamental research framework useful for helping educators and researchers to enhance student interest and retention on video-based learning.