In modern-day learning environments, the use of Natural Language Processing (NLP) to uncover meaningful information from text sources is becoming more and more common. This project is focused on the creation of a software application using topic modeling to examine student assessments of university performance. Through the use of advanced NLP algorithms, the app seeks to identify the most often expressed challenges and issues raised by students. This allows for quick identification of issues that are most prevalent in the dataset, which can then be addressed quickly to affect the student population significantly. This research delves into the use of topic modeling, with the help of Natural Language Processing (NLP), to study student feedback and derive actionable insights. Through the use of methodologies such as Latent Dirichlet Allocation (LDA), this research seeks to computerize the extraction of salient themes from vast amounts of student feedback, transcending the conventional labor-intensive method. The process entails extracting data from various sources, strict pre-processing, and the application of LDA to reveal latent topics.