Categorizing Well-Written Course Learning Outcomes Using Machine Learning

Aim/Purpose: This paper presents a machine learning approach for analyzing Course Learning Outcomes (CLOs). The aim of this study is to find model that can check whether CLO well written or not. Background: use algorithms has been, since many years, prominent solution predict learner performance in Outcome Based Education. However, the CLOs definition still presenting big handicap faculties. There lack supported tools and models permit Consequently, educators need an expert quality education validate outcomes their courses. Methodology: A novel method named CLOCML (Course Classification using Machine Learning) proposed develop predictive paraphrasing. new dataset entitled CLOC Classes) purpose been collected then undergone pre-processing phase. We compared 4 predicting classification. Those are Support Vector (SVM), Random Forest, Naive Bayes XGBoost. Contribution: application may help faculties make well-defined correct CLOs' measures order improve addressed students. Findings: best classification was SVM. It able detect class with accuracy 83%. Recommendations Practitioners: would recommend both faculties’ members reviewers informed decision about nature given course outcome. Recommendation Researchers: highly endorse researchers apply more various disciplines compare between them. also future studies investigate on importance its impact credibility Key Performance Indicators (KPIs) values during accreditation process. Impact Society: findings confirm results several other who outcome-based education. right will student get idea performances be measured at end course. Moreover, each faculty take appropriate actions suggest suitable recommendations after his Future Research: research improved by larger dataset. could deep reach accurate results. Indeed, strategy checking overlaps integrated.