This paper aims the proposal of model and its subsequent application of data mining techniques in a set of students answers collected during an Institutional Evaluation. Using Educational Data Mining, the proposed model looks for new categories of analysis in the student's discourse and contribute to Teachers Evaluation effectiveness and promotes reflections about teaching practices. Therefore, the authors propose an Institutional Teaching Evaluation model that applies, among others, the Sentiment Analysis to identify which teaching practices are positive or negative from the perspective of students from Higher Education Institution.