Data Science and Intelligent Computing Techniques
POGIL Data Analysis Employing Classification Algorithms to Examine Student Performance
Authors: Sahil Parab, Priyanshu Singh, Anjali Yeole and Maya Bhat
Publishing Date: 05-11-2023
ISBN: 978-81-955020-2-8
Abstract
Education is a fundamental and essential necessity that enhances the potential of everyone. It holds significance for achieving life goals and personal development. This study employs data mining classification techniques to analyze student data from the Vivekananda Education Society Institute of Technology in Chembur, Mumbai. The goal is to determine whether there exists a discernible pattern between the grades achieved by students instructed using POGIL (Process Oriented Guided Inquiry Learning) and those taught through traditional methods. POGIL represents a collaborative learning approach that integrates Guided Inquiry into a cyclic framework of concept generation, investigation, and application [2]. The student cohort was divided into two groups: one received instruction through the POGIL methodology, while the other experienced traditional teaching methods. Subsequent tests were administered to assess the performance of each group. Upon analyzing the collected data, it was revealed that students exposed to the POGIL learning method exhibited superior scores. Finally, a predictive model was developed to estimate the potential score increase for students adopting the POGIL methodology.
Keywords
J48 decision tree, K-nearest neighbour, Random Forest Classifier, logistic Regression, WEKA
Cite as
Sahil Parab, Priyanshu Singh, Anjali Yeole and Maya Bhat, "POGIL Data Analysis Employing Classification Algorithms to Examine Student Performance", In: Satyasai Jagannath Nanda and Rajendra Prasad Yadav (eds), Data Science and Intelligent Computing Techniques, SCRS, India, 2023, pp. 569-581. https://doi.org/10.56155/978-81-955020-2-8-52