A Data Analytics-based Approach for Quantitative Exploration of the Relationship between Engineering Programs Majors and Educational Objectives

In outcome-based education, Program Education Objects (PEOs) are essential components around which all program’s activities are centered. They represent graduates professional and career accomplishments within few years of graduation. In this paper, the relationship between the academic majors and PEOs of engineering programs is questioned and a data analytics-based approach to answer this question is proposed. More specifically, this paper applies three wellknown data correlation measures, namely pointwise mutual information, correlation coefficient and odds ratio, to a PEOs dataset extracted from the self-study reports of a set of engineering programs. The PEOs dataset has been linguistically pre-processed through cleaning, annotation using a set of PEOs labels and projection to break down each multi-PEOs label data instance into several single PEOs data instances. After that, the three measures are applied to measure the relationship between Programs’ Majors (PMs) and PEOs. The obtained results are then ranked based on PMsPEOs correlation strength and the agreement analysis among the three measures show a remarkable consistency among them in their evaluation of the relationship between PMs and PEOs. Finally, the overall ranking of PEOs within each PM, computed as a majority vote of the ranking of the three measures, show that each PM has a unique pattern of ranked PEOs. This suggests that the nature of PM plays a key role in determining the PM-PEOs relationship pattern. The obtained PMsPEOs quantitative correlations are very beneficial to the academicians particularly when designing new programs or reviewing existing ones.