Prediction of pre-service teachers' academic self-efficacy through machine learning approaches

Oct 15, 2026

This study examines how pre-service teachers’ beliefs in academic engagement, student burnout, and proactive strategies predict academic self-efficacy using machine learning. The sample includes 446 pre-service teachers from Sivas Cumhuriyet University, Faculty of Education. Data were collected with the Academic Self-Efficacy Scale, Academic Involvement Scale, Maslach Burnout Inventory—Student Scale, and Proactive Strategy Scale. Linear regression and artificial neural networks (ANNs) showed that engagement and proactive strategy positively relate to self-efficacy, burnout negatively relates, and ANNs predict it more effectively.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Introduction

Theoretical framework: Academic self-efficacy

African Educational Research Journal Vol. 11(1), pp. 32-44, January 2023 DOI: 10. 30918/AERJ.111.22.083 ISSN: 2354-2160 Full Length Research Paper Prediction of pre-service teachers' academic selfefficacy through machine learning approaches Hatice Yildiz Department of Educational Sciences, Faculty of Education, Sivas Cumhuriyet University, Sivas, Turkey. Accepted 12 January, 2023 | ABSTRACT
The aim of this study was to investigate the extent to which pre-service teachers' belief in academic engagement, student burnout, and proactive strategies predicts academic self-efficacy through machine learning approach. The study group consisted of 446 pre-service teachers at Sivas Cumhuriyet University, Faculty of Education. The Academic Self-Efficacy Scale, Academic Involvement Scale, Maslach Burnout Inventory-Student Scale, and Proactive Strategy Scale were used for data collection. In data analysis, two different machine learning approaches were used; linear regression and artificial neural networks (ANNs) . As a result of the regression analysis, a positive, and significant relationship was found between the academic self-efficacy of pre-service teachers, their academic engagement, and proactive strategy. Also, there was a negative and significant relationship between pre-service teachers' academic self-efficacy and academic burnout. Considering the results of the regression analysis, academic engagement, academic burnout, and proactive strategy together explained 38% of academic self-efficacy. When the ANNs results were examined, it was seen that these three variables explained 77% of academic self-efficacy. Therefore, it was understood that ANNs perform better than multiple regression in predicting academic self-efficacy.
Keywords: Academic self-efficacy, academic engagement, student burnout, proactive strategies, multiple regression, artificial neural networks. | | --- | | E-mail: yi[ldiz_htc@yahoo.com](ldiz_htc@yahoo.com). | INTRODUCTION The expeditious development in data analysis in the last years has made it important how to extract valuable information from huge volumes of data (Xu et al. , 2021) . Artificial intelligence (AI) applications that imitate human characteristics such as learning, perception, problemsolving, and reasoning have been rapidly applied in many areas in recent years (Abdallah et al. , 2020) . Artificial neural networks (ANNs), an important AI technique, have attracted great attention due to their features such as processing big data, mapping relationships, and predicting outcomes (Wang et al. , 2018) . ANNs use probabilities of all interactions between predictor variables to better predict the outcome variable (Cascallar et al. , 2015) and offer us the opportunity to obtain a prediction even when there is a nonlinear relationship between independent, and dependent variables (Somers and Casal, 2009) . ANNs also enable “the analysis of vast volumes of information, and the construction of predictive models regardless of the statistical distribution of the data” (Garson, 2014) . However, since more familiar analyses such as multiple linear regression are used in educational research, the use of ANNs has not yet become widespread (Bonsaksen, 2016) . Theoretical framework Academic self-efficacy Self-efficacy means to one’s views about the ability to deal with certain academic tasks (Owen and Froman, 1988; Sharma and Nasa, 2014) . This definition has two important aspects. First, self-efficacy is one's belief in his Yildiz 33 ability and therefore may differ from one's actual ability ina particular subject. The second important aspect is the idea that individuals use these judgments while trying to reach some goals (Artino Jr, 2012) . According to Bandura (1977), personal efficacy expectations are based on four sources: Performance achievements, vicarious experience, verbal persuasion, and emotional arousal. Performance achievements are specifically based on personal experie

FAQs

What variables does the study use to predict academic self-efficacy?

It predicts academic self-efficacy using academic engagement, student burnout, and proactive strategies.

Which data collection instruments are used in the study?

The Academic Self-Efficacy Scale, Academic Involvement Scale, Maslach Burnout Inventory—Student Scale, and Proactive Strategy Scale are used to collect data.

How do the machine learning methods compare in predicting self-efficacy?

Regression analysis indicates a weaker predictive contribution, while the ANNs results show stronger explanatory power for academic self-efficacy.

Oct 15, 2026

Uploaded by eBook King