Document Type

Conference Paper


This item is available under a Creative Commons License for non-commercial use only

Publication Details

Presented at the Higher Education in Transition Symposium November 2 - 4, 2016 in Oshawa, Ontario, Canada


Learning analytics is an evolving discipline with capability for educational data analysis to enable better understanding of learning processes. This paper reports on learning analytics research at Institute of Technology Blanchardstown, Ireland, that indicated measureable factors can identify first year students at risk of failing based on data available prior to commencement of first year of study. The study was conducted over three years, 2010 to 2012, on a student population from a range of academic disciplines (n=1,207). Data was gathered from both student enrolment data maintained by college administration, and an online, self-reporting tool administered during induction sessions for students enrolling into the first year of study. Factors considered included prior academic performance, personality, motivation, self- regulation, learning approaches, learner modality, age and gender. A k-NN classification model trained on data from the 2010 and 2011 student cohort, and tested on data from the 2012 student cohort correctly identified 74% of students at risk of failing. Some factors predictive of at-risk students are malleable, and relate to an effective learning disposition; specifically, factors relating to self-regulation and motivation. This paper discusses potential benefits of measurement of learner disposition.