Abstract:

Discovering student’s personality traits from discussed topics on different social media platforms like Twitter, Facebook, etc. is in the heart of research of institutions of higher education. Applications such as myPersonality on Facebook are used to collect data about user’s personality. Using data sets from social medias or data from applications are used in many studies for training various machine learning classifiers.

The purpose of this study is to use datasets from one of the social media platform GroupMe of one computer science course, apply supervised machine learning algorithms to get sentiment analysis about the overall student views on course as per the following: if the value is greater than 3 which is the average value for the scale of the field, then the comment is considered as a positive sentiment (Classification=1). On the other hand, if the value is less than 3, then the comment is considered as a negative sentiment (Classification=0). Another approach of classification used in this study, is training the available dataset into the machine learning algorithms like Multinominal Naïve Bayes (NB), Random Forest Classifier and Regressor, Support Vector Machine (SVM) to classify students based on their personality traits according to OCEAN personality traits(Openness, Conscientiousness, Extroversion, Agreeableness, and Neuroticism). These five traits represent broad domains of human behavior and account for differences in both personality and decision making. The proposed framework shows an accuracy of 80 percent compared to traditional way of using surveys to find out personality traits. We believe that students’ comments are a good source to capture the overall students’ sentiment as well as defining the personality traits. Predicting the personality of a student early in the semester might lead to an effective intervention to help student succeed in the course.

Keywords:

Machine learning, student profiling, sentiment analysis.