Related Experiment Video
Updated: May 5, 2026
Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
Published on: May 31, 2019
Development and Validation of Artificial Intelligence Addiction Scale for Researchers: A Methodological Study
Ahmed Abdelwahab Ibrahim El-Sayed1, Samira Ahmed Alsenany2, Maha Gamal Ramadan Asal3
1Nursing Administration Department, Faculty of Nursing, Alexandria University, Alexandria, Egypt, alexu.edu.eg.
Background:
The integration of artificial intelligence (AI) tools into research has brought significant advancements, enhancing efficiency, innovation, and productivity across various academic disciplines. However, alongside these transformative benefits, the growing dependence on AI tools has raised concerns regarding overreliance and the potential for addictive behaviors among researchers. Despite the widespread adoption of AI among the researchers, there remains a notable gap in the availability of validated instruments specifically designed to assess AI addiction within this context.
Objective:
To develop a scale to measure AI addiction among researchers and evaluate its psychometric properties.
Design:
A methodological design was employed, consisting of two phases: scale development and psychometric evaluation.
Methods:
Items were generated through a comprehensive literature review and semistructured interviews to capture AI addiction attributes. The scale's psychometric properties-including content validity, face validity, construct validity, and internal consistency reliability-were assessed. Data from a convenience sample of 718 nursing researchers were randomly divided into two independent subsamples for exploratory factor analysis (EFA) and confirmatory factor analysis (CFA). Reliability was evaluated using Cronbach's alpha, McDonald's omega, split-half reliability, and corrected item-total correlations.
Results:
The finalized scale comprises 22 items across five dimensions: compulsive behavior, overdependency, functional impairment, withdrawal, and tolerance. EFA identified a five-factor structure explaining 73.66% of the variance. CFA validated the structure with robust fit indices for first order (χ 2/DF = 2.289, CFI = 0.962, and RMSEA = 0.06) and second order (χ 2/DF = 2.243, CFI = 0.962, and RMSEA = 0.059) models. The scale demonstrated excellent internal consistency and reliability, with Cronbach's alpha (α = 0.924), McDonald's omega (ω = 0.870), and a Spearman-Brown split-half coefficient of 0.814. Moderate interfactor correlations (r = 0.41-0.62) confirmed its multidimensionality.
Conclusion:
The researchers' AI addiction scale is a valid and reliable tool for assessing AI addiction among researchers, providing a robust framework to evaluate compulsive behavior, dependency, functional disruption, withdrawal symptoms, and tolerance.
