Student opinions about personalized recommendation and feedback based on learning analytics

Abstract

There is a growing interest in the use of learning analytics in higher education institutions. Learning analytics also appear to have the potential to be used to provide personalized feedback and support in online learning. However, when the literature is examined, the use of learning analytics for this purpose appears as a gap to be investigated. This research aims to examine the opinions of pre-service teachers about the personalized recommendation and guidance feedback based on learning analytics. The research was carried out on 40 pre-service teachers in the Computer I course, which was conducted according to the flipped learning model for 12 weeks. Throughout the research process, personalized feedback based on learning analytics was provided by researcher (the researcher is also the teacher of the Computer I course) to preservice teachers at the end of each week. Accordingly, the students’ weekly learning management system (LMS) obtained learning analytics results from the log data related to their usage behavior. Then, the researcher prepared personalized recommendation and guidance messages based on learning analytics results. Learning analytics results and related recommendations and guidance messages were sent via LMS (from the messaging tool) as feedback. This process was done for each pre-service teacher by the researcher every week during the research process. The data of the research were obtained with a semi-structured opinion form and content analysis was made in the analysis of the data. As a result of the research, beneficial aspects and limitations of personalized recommendation and guidance feedback based on learning analytics from the perspective of pre-service teachers were revealed. In line with the results obtained from the research, various suggestions were made for the design and use of feedback messages based on learning analytics.