Evaluating sustainability of mobile learning framework for higher education: a machine learning approach

Abstract

PurposeThe purpose of this study is to evaluate the sustainability of the proposed mobile learning framework for higher education. Most sustainability evaluation studies use quantitative and qualitative methods with statistical approaches. Sometimes, in previous studies, machine learning models were utilized conventionally.Design/methodology/approachIn the proposed method, the authors use a novel machine learning-based ensemble approach with severity indexes to evaluate the sustainability of the proposed mobile learning system. In this severity indexes, consider the cause-and-effect relationship to identify the hidden correlation among sustainability factors. Also, the proposed novel sustainability evaluation algorithm helps to evaluate and improve sustainability iteratively to have an optimal sustainable mobile learning system. In total, 150 learners and 150 teachers in the university community engaged in the study by taking the sustainability questionnaire. The questionnaire consists of 20 questions that represent 20 sustainable factors in five sustainability dimensions, i.e. economic, social, political, technological and pedagogical.FindingsThe results reveal that the proposed system has achieved its economic and pedagogical sustainability. However, the results further reveal that the proposed system needs to be improved on technological, social and political sustainability.Originality/valueThe study focused novel machine learning approach and technique for evaluating sustainability of the proposed mobile learning framework.

Artificial Intelligence and Business Studies: Study Cycle Differences Regarding the Perceptions of the Key Future Competences

“…As we input more data, the accuracy of the algorithm's predictions increases. To identify specific patterns, statistics play a crucial role in studying the data, and providing guidance for analyzing and presenting raw data [26]. This approach is widely used in computer vision and speech analysis to uncover previously unseen patterns.…”