e-Behaviour, personality and academic performance analysis for intervention

Abstract

Post-secondary educational institutions have a concerningly low rate of completion. Problems include a lack of student support, a student’s social, cultural and economic background, and inability to adapt to the curriculum. This study provides insight into the relationship between e-Behaviour, personality and performance. Student perfor mance analysis involves data modelling that enables the formulation of hypotheses and insights about student behaviour and personality. While the automation of such data pipelines is efficient and economical, it still requires a thorough analysis of data and the results obtained from its usage. To achieve the exploratory data anal ysis and prediction objectives of this research, the algorithms used are Regression Analysis, Decision-Tree, Support Vector Machine, k-Means clustering, k-Nearest Neighbours, and the Long Short-Term Memory. Our procedures provide methodol ogy to timeously identify students who are likely to become at risk of poor academic performance. For the education sector, this study is valuable because it presents an approach to examining the extrinsic influences – e-Behaviour and personality – on performance. We extract online behaviours as proxies to Extraversion and Consci entiousness, which have been proven to correlate with academic performance. The proxies of Extraversion and Conscientiousness yield significant (p < 0.05) pop ulation correlation coefficients for the personality traits against grade: 0.846 for Extraversion and 0.319 for Conscientiousness. Using engineered e-Behaviour and personality features, we obtained a classification accuracy (κ) of students at risk of 0.51. Lastly, we design an intervention process that supplements existing perfor mance analysis and intervention methods