Exploring the Significant Predictors to the Quality of Master’s Dissertations

• Main Authors: Zhemin Li, Yanwu Li, Zheng Xie
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Postgraduate education; dissertation quality; random forest
• Online Access: https://ieeexplore.ieee.org/document/8961093/

The quality of masters' dissertations is an important index of graduate education, which can be in part reflected through the grades given by experts. This study aims to find the factors positively correlated to the grades, and then use them to predict the grades and quality of dissertations. We applied four typical machine learning models to calculate the impacts of several factors extracted from the contents of dissertations on the grades. It shows that the random forest model outperforms logistic regression, support vector machine, and naive Bayes on recognizing the dissertations with a high grade. It also shows that the quantity of publications is the most important predictor to the grades, compared with the quantity of publications, the length of dissertations, the quantity and quality of references. And the quality of references is a significant predictor of producing high quality publications. Those findings can be utilized to predict and recognize high quality dissertations.