Investigating Computational Identity and Empowerment of The Students Studying Programming: A Text Mining Study

Abstract

In this study, it is aimed to predict the data obtained from the answers given by the students who receive programming education to open-ended questions with text mining algorithms. Thus, text-based data on computational identity and programming empowement were analyzed and the performances of different algorithms were compared. The participants of the research consisted of 646 students whose age range was between 12-20 and who received programming education. An electronic form consisting of open-ended questions was prepared to collect the opinions of the students who received programming education. A total of six open-ended questions have been prepared about computational identity and (3 questions) and programming empowerment (3 questions). The text mining process was followed in the analysis of the data set. Analyzes were made in Python 3.8 program. In the study, the performance of Word2vec (W2v) and Term Frequency-Inverse Document Frequency (TF-IDF) word representation methods with five machine learning algorithms were compared: (a) Logistic regression, (b) Decision tree, (c) Support Vector Machines, (d) Random Forest, (e) Neural Network. Regarding computational identity, the highest prediction accuracy was found in artificial neural network (tf-idf) and logistic regression (tf-idf) algorithms. These algorithms have an accuracy rate of 93% regarding computational identity. It was determined that the logistic regression (tf-idf) method reached the highest accuracy prediction rate (96%) in programming empowement. Following this method, the accuracy rate of random forest (tf-idf), support vector machine (tf-idf) and artificial neural network (tf-idf) algorithms was 94%. The fact that these obtained values are above 90% indicates that the estimation performance is sufficient.