A Data-driven Analysis of Rate-my-professors’ Student Reviews on Universities

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

Date of Award

Summer 2017

Abstract

Assessing the educational qualities of the academic institutes is essential for future improvements. The RateMyProfessors.com (RMP) data is a helpful resource for this purpose, since it contains self-selected students’ quantitative scores and verbal reviews for both professors and institutes, which could be used to identify the potential areas for improving the educational qualities of the academic institutes. With its importance, there has been a body of research analyzing the RMP data, but the existing research simply focused on the quantitative scores or considered only professors’ reviews. This project initiates a new research approach that incorporates the verbal reviews as a means for the qualitative analysis with the quantitative scores for analysis. To this end, I developed a new methodology to enable a data-driven analysis of the RMP’s university reviews, with the following steps: (i) sentiment analysis of the verbal comments, (ii) aspect-based sentiment analysis to extract the specific aspect of the verbal comments, (iii) clustering of institutes with respect to the sentiment analysis results, and (iv) correlation study with the quantitative scores for interpretation. With this project, I present new findings and observations made with the RMP dataset pertinent to Texas universities and colleges that can be beneficial to improve the quality of the academic institutes. Further, the findings indicate that many private universities in Texas received positive reviews on aspects like reputation, happiness, faculty, and professors. Similarly, many universities in Texas were given negative reviews on aspects like social, internet, location, and campus.

Advisor

Jinoh Kim

Subject Categories

Computer Sciences | Data Science | Physical Sciences and Mathematics

Link to Full Text

Share

COinS