Thesis submitted for degree in Computational Linguistics,
The Graduate Center, City University of New York
Student reviews often make reference to professors’ physical appearances. Until recently RateMyProfessors.com, the website of this study’s focus, used a design feature to encourage a “hot or not” rating of college professors. In the wake of recent #MeToo and #TimesUp movements, social awareness of the inappropriateness of these reviews has grown; however, objectifying comments remain and continue to be posted in this online context. This paper describes two supervised text classifiers for detecting objectifying commentary in professor reviews. From an ensemble these classifiers, the resulting model tracks objectifying commentary at scale. Correlations between objectifying commentary, changes to the review website interface, and teacher gender are measured across a ten-year period.