Forecasting E-Mentoring Effectiveness using Data Mining Approach

E-mentoring is a very important aspect of student well-being and is known to promote effective learning and better academic program out-comes. This study uses structural equation modelling (SEM) to predict e-mentoring effectiveness based on five predicting variables namely psychological-emotional support (PES), goal setting (GS), academic support (AS), role model (RM) and digital competence (DC). Four factors are significant predictors on e-mentoring effectiveness with academic support being the most significant predictor. This indicates the seriousness and maturity levels of the students are much needed to succeed in a professional computer applications program. Digital competence is not a significant predictor and this suggests that for the mentor and protégé the mentoring outcomes are more important rather than the mode.