Investigating computational identity and empowerment of the students studying programming: A text mining study

Authors : Nilüfer ATMAN USLU, Aytuğ ONAN

Pages : 29-45

View : 46 | Download : 53

Publication Date : 2023-06-24

Article Type : Research Paper

Abstract :This study aimed to predict the texts obtained from the answers given by the students receiving programming education to open-ended questions, with text mining algorithms. Thus, an attempt was made to analyze text-based data in research on computational identity and programming empowerment and to compare the performances of different algorithms. The participants of the study consisted of 646 students studying programming with age range varies between 12-20. An electronic form consisting of open-ended questions was prepared to collect the opinions of the students who received programming education. There are a total of six open-ended questions about computational identity insert ignore into journalissuearticles values(3 questions); and empowerment insert ignore into journalissuearticles values(3 questions);. The text mining process was followed in the analysis of the data set. Analyzes were carried out in Python 3.8 program In this study, Word2vec insert ignore into journalissuearticles values(W2v); and Term Frequency-Inverse Document Frequency insert ignore into journalissuearticles values(TF-IDF); word representation methods were used. Five machine learning algorithms compared in this study: insert ignore into journalissuearticles values(a); Logistic regression, insert ignore into journalissuearticles values(b); Decision tree, insert ignore into journalissuearticles values(c); Support Vector Machines, insert ignore into journalissuearticles values(d); Random Forest, insert ignore into journalissuearticles values(e); Artificial Neural Network. Concerning computational identity, it was found that the highest estimation accuracy was in artificial neural network insert ignore into journalissuearticles values(tf-idf); and logistic regression insert ignore into journalissuearticles values(tf-idf); algorithm. These algorithms have an accucary rate of 93% regarding computational identity. When the text-data related to programming empowerment was analyzed, it was determined that the logistic regression insert ignore into journalissuearticles values(tf-idf); method reached the highest accuracy prediction rate insert ignore into journalissuearticles values(96%);. Following this method, random forest insert ignore into journalissuearticles values(tf-idf);, support vector machine insert ignore into journalissuearticles values(tf-idf); and artificial neural network insert ignore into journalissuearticles values(tf-idf); algorithms predicted with 94% accuracy. The fact that these obtained scores are above 90% can be interpreted as sufficient estimation performance.
Keywords : Bilgi işlemsel kimlik, Programlama, Yetkilendirme, Metin madenciliği