DOI: 10.53850/joltida.1440845 ISSN: 2458-8350
Artificial intelligence literacy scale: A study of reliability and validity in Turkish university students
Arzu Deveci Topal, Asiye Toker Gökçe, Canan Dilek Eren, Aynur Kolburan Geçer Abstract: This study aims to adapt to Turkish the "Scale for the assessment of non-experts' AI literacy" developed by Laupichler et al (2023). The scale consists of 31 items with three sub-dimensions: technical understanding, critical appraiaal, and practical applications. The data required for the validity and reliability study of the scale was collected from 642 undergraduate and graduate students studying in different departments of a state university in the fall semester of the 2023-2024 academic year. First of all, CFA was applied to the data according to the factor structure in the original scale, but as acceptable fit values could not be obtained as a result of the analysis, exploratory factor analysis was performed. While 325 of the collected data were used in exploratory factor analysis, 317 were used in confirmatory factor analysis. In the reliability analysis of the factor structure determined by EFA, KMO was calculated as =0.948. It was determined that the scale items were collected in 3 factors and explained 61.1% of the total variance ("critical thinking" is 25.8%, "technical knowledge" is 25.2%, and "practical applications" explains 10.2% of the total variance). As a result of EFA, it was seen that the sub-dimensions of some of the items in the original scale had changed, and since the factor load values of three items were very close to each other, they were removed from the scale. A As a result of CFA, which was conducted to evaluate whether the data supported the hypothesized relationships between the measured variables, Cronbach's Alpha value was found to be 0.90. As a result of the CFA analysis conducted with the 3 sub-dimensions and 28 items in the scale, the Chi-square value (X²=2.85; df=345, N=317, p< .001), which is the fit index of the model, has a good fit and is significant, SRMR=0.0545. and RMSEA=0.077 values and fit indices, it can be said that the model has an acceptable fit. The adapted scale is expected to be used in the future by educators, policymakers, and researchers in Turkish-speaking countries to establish a standardized framework for AI literacy and AI courses.