Using Sentiment Analysis to Identify Student Emotional State to Avoid Dropout in E-Learning

Abstract

Dropping out of school comes from a long-term disengagement process with social and economic consequences. Being able to predict students’ behavior earlier can minimize their failures and disengagement. This article presents the SASys architecture based on a lexical approach and a polarized frame network. Its main goal is to define the author’s sentiment in texts and increase the assertiveness of detecting the sentence’s emotional state by adding author information and preferences. The author’s emotional state begins with the phrase extraction from virtual learning environments; then, pre-processing techniques are applied in the text, which is submitted to the complex frame network to identify words with polarity and the author’s text sentiment. The flow ends with the identification of the author’s emotional state. The proposal was evaluated by a case study, applying the sentiment analysis approach to the student school dropout problem. The results point to the feasibility of the proposal for asserting the student’s emotional state and detection of student risks of dropout.