ระบบจัดเก็บและค้นหางานวิจัยอัจฉริยะ

Using Machine Learning Techniques to Compare Classification Model Efficiency for Analyzing Library Usage Factors and Student Academic Performance

ผศ.ดร.ณัฐรฐนนท์ กานต์รวีกุลธนา | Machine learning Classification models Academic libraries

จำนวนผู้เข้าชม

Using Machine Learning Techniques to Compare Classification Model Efficiency for Analyzing Library Usage Factors and Student Academic Performance

เปิดลิงก์เอกสาร

DOI Link

Collection	RMUTK Research Repository (RMUTK IR) บทความประชุมวิชาการ — Proceedings
ID RMUTK Digital	RMUTK000135
Title	Using Machine Learning Techniques to Compare Classification Model Efficiency for Analyzing Library Usage Factors and Student Academic Performance
Alternative title	Using Machine Learning Techniques to Compare Classification Model Efficiency for Analyzing Library Usage Factors and Student Academic Performance
Authors	ผศ.ดร.ณัฐรฐนนท์ กานต์รวีกุลธนา
Faculty	คณะบริหารธุรกิจ
Volume / Issue / Pages	pp.11-21
Conference	The 6th Asia Joint Conference on Computing (AJCC2025)
Conference Date	2025-04-23
Conference Location	Kansai Kenshu Center (KKC), Osaka, Japan
Year	2568
Level	ระดับนานาชาติ
DOI	https://edas.info/web/ajcc2025/authors.html
ISBN / ISSN	-
Funding Source	-
Abstract	This research paper examines the effectiveness of different machine learning (ML) models in analyzing how library usage influences the academic performance of Thammasat University students. By leveraging a comprehensive dataset that contains library interactions such as library of things (LoT) services, book borrowing and returning, and space services, this study evaluates five ML models: decision tree, k-nearest neighbors, Naïve Bayes, random forest, and support vector machine. The primary goal is to identify which library services and facilities significantly impact student success to provide actionable insights for customizing library offerings and enhancing academic outcomes. Results were that the decision tree model was particularly effective, delivering precise, reliable classification of factors affecting student academic performance into training data and data testing, using the 10-fold cross-validation procedure. These findings help demonstrate practical applications of ML in educational contexts and facilitate library strategic planning and management.
Abstract (EN)	This research paper examines the effectiveness of different machine learning (ML) models in analyzing how library usage influences the academic performance of Thammasat University students. By leveraging a comprehensive dataset that contains library interactions such as library of things (LoT) services, book borrowing and returning, and space services, this study evaluates five ML models: decision tree, k-nearest neighbors, Naïve Bayes, random forest, and support vector machine. The primary goal is to identify which library services and facilities significantly impact student success to provide actionable insights for customizing library offerings and enhancing academic outcomes. Results were that the decision tree model was particularly effective, delivering precise, reliable classification of factors affecting student academic performance into training data and data testing, using the 10-fold cross-validation procedure. These findings help demonstrate practical applications of ML in educational contexts and facilitate library strategic planning and management.
Keywords (TH)	Machine learning Classification models Academic libraries Library services Student performance
Keywords (EN)	Machine learning Classification models Academic libraries Library services Student performance
Access Level	Open Access (เปิดสาธารณะ)

ลิงก์แหล่งเผยแพร่

เอกสารฉบับเต็ม (ลิงก์ภายนอก)

https://edas.info/web/ajcc2025/authors.html

เปิดลิงก์