Initial validation of the general attitudes towards Artificial Intelligence Scale

Abstract

A new General Attitudes towards Artificial Intelligence Scale (GAAIS) was developed. The scale underwent initial statistical validation via Exploratory Factor Analysis, which identified positive and negative subscales. Both subscales captured emotions in line with their valence. In addition, the positive subscale reflected societal and personal utility, whereas the negative subscale reflected concerns. The scale showed good psychometric indices and convergent and discriminant validity against existing measures. To cross-validate general attitudes with attitudes towards specific instances of AI applications, summaries of tasks accomplished by specific applications of Artificial Intelligence were sourced from newspaper articles. These were rated for comfortableness and perceived capability. Comfortableness with specific applications was a strong predictor of general attitudes as measured by the GAAIS, but perceived capability was a weaker predictor. Participants viewed AI applications involving big data (e.g. astronomy, law, pharmacology) positively, but viewed applications for tasks involving human judgement, (e.g. medical treatment, psychological counselling) negatively. Applications with a strong ethical dimension led to stronger discomfort than their rated capabilities would predict. The survey data suggested that people held mixed views of AI. The initially validated two-factor GAAIS to measure General Attitudes towards Artificial Intelligence is included in the Appendix.