Abstract
Statement of Purpose (SOP) plays a vital role in the university admissions process as reviewers assess the personality of the students by reading their SOPs. In past, the Big Five personality traits of the students are assessed to predict their future academic performance. An exciting application of machine learning is the personality assessment using personality traits and behavior. In this paper, our focus is on developing a deep learning-based personality assessment model for the detection of Big Five Personality traits from SOP and mapping them to speculate a student's academic performance at the university. Our proposed model uses Long-Short Term Memory (LSTM), Convolutional Neural Network (CNN) and Bi-Directional LSTM (Bi- LSTM) architectures to extract features and predict ratios of Big Five traits in the SOP. The proposed model has been trained and tested on an essays' dataset and 400 students' SOP collected from computer science undergraduate students. Maximum accuracy achieved for essays dataset is 88.2 % and for student's personal statement is 67.0 % with FastText Embedding.