Abstract: Sentiment Analysis is a field of Natural Language Process-ing which aims at classifying the author’s sentiment in text.This paper first describes a sentiment analysis model for stu-dents’ comments about professor performance. The modelachieved impressive results for comments collected from stu-dent surveys conducted at a private university in 2019/20.Then, it applies the model to different scenarios: (i) in-person classes taught in 2019 (pre-COVID); (ii) the emer-gency shift to online, synchronous classes taught in the firstsemester of 2020 (early-COVID); and (iii) the planned onlineclasses taught in the second semester of 2020 (late-COVID).The results show that students acknowledged the effort pro-fessors did to keep classes running during the first semesterof 2020, and that the enthusiasm continued throughout thesecond semester. Furthermore, the results show that stu-dents evaluated professors’ performance for online courses better than for in-person courses.