Sentiment Analysis in Higher Education: A Systematic Mapping Reviewbased Deep Neural Network

In the last years, sentiment analysis (SA) has attracted increasing interest in the text mining area. It increasingly becomes a popular research area for opinion mining in education that analyses and understands students’ opinions toward their institutions for improving the quality of decision-making. In this study, a systematic review was conducted to explore the recent application of sentiment analysis in higher education; to classify SA techniques and methods commonly and successfully used in the higher education domains. A systematic mapping review was applied to 840 articles, and 22 related studies are selected based on the study’s criteria. The findings revealed that the prior studies mainly focus on six domains for applying SA in the higher education context and the teaching quality evaluation was the most addressed domain. The study also found that applying specific SA techniques could be the best tool for institutions to solve particular learning problems and a useful tool for improving higher education institutions’ quality and evaluating the teaching process as well as teachers’ performance. This study’s main contribution is the new categorizations of the SA applications techniques in higher education to provide a closely full image of SA-related tools and areas.

The authors declare no conflict of interest.

Not applicable

The datasets used in this study are openly available at [repository link] and the source code is available on GitHub at [GitHub link].

This work did not receive any external funding.