Determining student's online academic performance using machine learning techniques

• Autorzy: Islam, Atika , Bukhari, Faisal , Sattar, Muhammad Awais , Kashif, Ayesha

Warianty tytułu

PL

Ocena wydajności akademickiej studentów w nauce online za pomocą technik uczenia maszynowego

• Języki publikacji: EN

Abstrakty

EN

Predicting student's academic performance during online learning has been considered a major task during the pandemic period. During the online mode of learning, academic activities have been affected in such a way that the management of educational institutions has planned to design support systems for predicting the student's performance to reduce the dropout ratio of the students and bring improvement in academic activities. During COVID-19, the main challenge is maintaining student's grades by predicting their academic performance using different techniques such as Education Data Mining and Learning Analytics. Different features have been identified related to the teaching mechanisms in online learning, which have a great impact on the improvement of academic performance. A high-quality dataset helps us to generate productive results, which in turn helps us to make effective decisions for promoting high-quality education. In this research, five prediction models for predicting academic performance have been proposed by collecting an imbalanced dataset of 350 students from the same computer science domain. After applying pre-processing techniques for cleaning the data, machine learning models have been applied, including K-Nearest Neighbor Classifier, Decision Tree, Random Forest, Support Vector Classifier, and Gaussian Naive Bayes. Results have been predicted for an imbalanced and balanced dataset after feature selection. Support Vector classifier has produced the best results in a balanced dataset with selected features by giving an accuracy of 96.89%.

PL

Przewidywanie wyników akademickich studentów podczas nauki online było uważane za ważne zadanie w okresie pandemii. W trakcie nauki w trybie online działalność akademicka była zakłócana w taki sposób, że zarządy instytucji edukacyjnych planowały projektowanie systemów wsparcia do przewidywania wyników studentów w celu zmniejszenia wskaźnika rezygnacji ze studiów i poprawy działalności akademickiej. Podczas COVID-19 głównym wyzwaniem jest utrzymanie ocen studentów poprzez przewidywanie ich wyników akademickich za pomocą różnych technik, takich jak Edukacyjna Analiza Danych i Analityka Edukacyjna. Zidentyfikowano różne cechy związane z mechanizmami nauczania w nauce online, które mają duży wpływ na poprawę wyników akademickich. Wysokiej jakości zestaw danych pomaga generować produktywne wyniki, które z kolei pomagają podejmować skuteczne decyzje na rzecz promowania wysokiej jakości edukacji. W tym badaniu zaproponowano pięć modeli predykcyjnych do przewidywania wyników akademickich, zbierając niezrównoważony zestaw danych 350 studentów z tej samej dziedziny informatyki. Po zastosowaniu technik przetwarzania wstępnego do oczyszczania danych, zastosowano modele uczenia maszynowego, w tym klasyfikator K-Najbliższych Sąsiadów, Drzewo Decyzyjne, Las Losowy, Klasyfikator Wektorów Wspierających oraz Naiwny Klasyfikator Bayesa Gaussowskiego. Wyniki przewidziano dla niezrównoważonego i zrównoważonego zestawu danych po selekcji cech. Klasyfikator wektorów wspierających wyprodukował najlepsze wyniki w zrównoważonym zestawie danych z wybranymi cechami, osiągając dokładność 96,89%.

Słowa kluczowe

PL

edukacyjna eksploracja danych; analityka uczenia się; losowy las; klasyfikator wektora wsparcia

EN

educational data mining; learning analytics; random forest; support vector classifier

• Czasopismo: Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
• Rocznik: 2024
• Tom: T. 14, nr 3
• Strony: 109--117
• Opis fizyczny: Bibliogr. 25 poz., tab., wykr.

Twórcy

autor

Islam, Atika

• Riphah International University, Riphah School of Computing and Innovation, Lahore, Pakistan,

autor

Bukhari, Faisal

• University of The Punjab, Faculty of Computing and Information Technology, Lahore, Pakistan,

autor

Sattar, Muhammad Awais

• Riphah International University, Riphah School of Computing and Innovation, Lahore, Pakistan,

autor

Kashif, Ayesha

• University of The Punjab, Faculty of Computing and Information Technology, Lahore, Pakistan,

Bibliografia

• [1] Akour I. et al.: Using machine learning algorithms to predict people’s intention to use mobile learning platforms during the COVID-19 pandemic: machine learning approach. JMIR Medical Education 7, 2021, e24032.
• [2] Altabrawee H., Ali O. A. J., Ajmi S. Q.: Predicting students’ performance using machine learning techniques. Journal of University of Babylon for pure and applied sciences 27, 2019, 194–205.
• [3] Aman F. et al.: A predictive model for predicting students academic performance. 10th International Conference on Information, Intelligence, Systems and Applications – IISA. IEEE, 2019, 1–4.
• [4] Arnold K. E., Pistilli M. D.: Course signals at Purdue: Using learning analytics to increase student success. 2nd International Conference on Learning Analytics and Knowledge, 2012, 267–270.
• [5] Baraniuk R.: Open education: New opportunities for signal processing. IEEE International Conference on Acoustics, Speech and Signal Processing – ICASSP, 2015.
• [6] Bhardwaj B. K., Pal S.: Data Mining: A prediction for performance improvement using classify cation. arXiv preprint arXiv:1201.3418, 2012.
• [7] Bhutto E. S. et al.: Predicting students’ academic performance through supervised machine learning. International Conference on Information Science and Communication Technology – ICISCT. IEEE, 2020, 1–6.
• [8] Borge N.: Artificial intelligence to improve education/learning challenges. International Journal of Advanced Enginering & Innovative Technology – IJAEIT 2, 2016, 10–13.
• [9] Chaudhury P. et al.: Enhancing the capabilities of student result prediction system. Second International Conference on Information and Communication Technology for Competitive Strategies, 2016, 1–6.
• [10] Clow D.: An overview of learning analytics. Teaching in Higher Education 2013, 18, 683–695.
• [11] Ever Y. K., Dimililer K.: The effectiveness of a new classification system in higher education as a new e-learning tool. Quality & Quantity 52, 2018, 573–582.
• [12] Gray G., McGuinness C., Owende P.: An application of classification models to predict learner progression in tertiary education. IEEE International Advance Computing Conference – IACC. IEEE, 2014, 549–554.
• [13] Huang S., Fang N.: Work in progress: Early prediction of students’ academic performance in an introductory engineering course through different mathematical modeling techniques. Frontiers in Education Conference Proceedings. IEEE, 2012, 1–2.
• [14] Kolo D. K., Adepoju S. A., Alhassan J. K.: A decision tree approach for predicting students academic performance. I.J. Education and Management Engineering 5, 2015, 12–19.
• [15] Kotsiantis S. B.: Use of machine learning techniques for educational proposes: a decision support system for forecasting students’ grades. Artificial Intelligence Review 37, 2012, 331–344.
• [16] Mueen A., Zafar B., Manzoor U.: Modeling and Predicting Students’ Academic Performance Using Data Mining Techniques. International Journal of Modern Education & Computer Science 8, 2016.
• [17] Osmanbegovic E., Suljic M.: Data mining approach for predicting student performance. Economic Review: Journal of Economics and Business 10, 2012, 3–12.
• [18] Oyedeji A. O. et al.: Analysis and prediction of student academic performance using machine learning. JITCE (Journal of Information Technology and Computer Engineering) 4, 2020, 10–15.
• [19] Rachburee N., Punlumjeak W.: A comparison of feature selection approach between greedy, IG-ratio, Chi-square, and mRMR in educational mining. 7th International Conference on Information Technology and Electrical Engineering – ICITEE. IEEE, 2015, 420–424.
• [20] Romero C., Ventura S.: Educational data mining: A survey from 1995 to 2005. Expert systems with applications 33, 2007, 135–146.
• [21] Said M. A., Idris M., Hussain S.: Relationship between Social Behaviour and Academic Performance of Students at Secondary Level in Khyber Pakhtunkhwa. Pakistan Journal of Distance and Online Learning 4, 2018, 153–170.
• [22] Sekeroglu B., Dimililer K., Tuncal K.: Student performance prediction and classification using machine learning algorithms. 8th International Conference on Educational and Information Technology, 2019, 7–11.
• [23] Singh A., Halgamuge M. N., Lakshmiganthan R.: Impact of different data types on classifier performance of random forest, naive bayes, and k-nearest neighbors algorithms. International Journal of Advanced Computer Science and Applications 8, 2017.
• [24] Thammasiri D. et al.: A critical assessment of imbalanced class distribution problem: The case of predicting freshmen student attrition. Expert Systems with Applications 41, 2014, 321–330.
• [25] Wolff A. et al.: Developing predictive models for early detection of at-risk students on distance learning modules. LAK Workshops, 2014.

Identyfikatory

DOI

10.35784/iapgos.6173