IJIET 2025 Vol.15(11): 2423-2435
doi: 10.18178/ijiet.2025.15.11.2438
doi: 10.18178/ijiet.2025.15.11.2438
Development of a Computer-Based Chemistry Misconception Detector Integrated with Item Response Theory
Achmad Rante Suparman*, Murtihapsari, and Apriani Sulu Parubak
Department of Chemistry Education, Faculty of Teacher Training and Education, Universitas Papua, Manokwari Papua Barat, Indonesia
Email: a.rante@unipa.ac.id (A.R.S.); m.murtihapsari@unipa.ac.id (M.); a.parubak@unipa.ac.id (A.S.P.)
*Corresponding author
Email: a.rante@unipa.ac.id (A.R.S.); m.murtihapsari@unipa.ac.id (M.); a.parubak@unipa.ac.id (A.S.P.)
*Corresponding author
Manuscript received January 15, 2025; revised April 1, 2025; accepted May 7, 2025; published November 13, 2025
Abstract—This study developed a computer-based chemistry misconception detection media integrated with Item Response Theory (IRT). Involving 595 students in small and large-scale trials, small-scale trials involving 55 students, and large-scale trials involving 540 students. The schools involved are schools with accreditation ratings A and B. This media is designed to identify misconceptions quickly and accurately. Analysis using R studio shows that in the Confirmatory Factor Analysis (CFA), all loading factors are positive, indicating that all questions have measured the appropriate factors and Root Mean Square Error of Approximation (RMSEA), Standardized Root Mean Square Residual (SRMR), Goodness-of-Fit Index (GFI), Normed Fit Index (NFI), Comparitive Fit Index (CFI), Incremental Fit Index (IFI), Relative Fit Index (RFI), and Tucker–Lewis Index (TLI) are proven to be fit, this indicates that the instrument construct is proven valid. The estimated value of the construct reliability using Construct Stability (CR) obtained a value > 0.5, indicating that the construct is proven reliable so that the developed detection media is proven valid and reliable. The item response theory analysis used is the Partial Credit Model (PCM) because it has a smaller Akaike Information Criterion (AIC) value. Further study in hierarchical cluster analysis using the silhouette method utilizing R Studio showed two clusters: high and low. The correlation between school accreditation and student ability based on high and low-ability clusters was analyzed using the Spearman rank correlation test and obtained a rho value of −0.006748223, which indicates a fragile relationship between the accreditation and cluster variables.
Keywords—confirmatory factor analysis, item response theory, misconception, R studio, silhouette method
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
Keywords—confirmatory factor analysis, item response theory, misconception, R studio, silhouette method
Cite: Achmad Rante Suparman, Murtihapsari, and Apriani Sulu Parubak, "Development of a Computer-Based Chemistry Misconception Detector Integrated with Item Response Theory," International Journal of Information and Education Technology, vol. 15, no. 11, pp. 2423-2435, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).