Computers have enabled diverse and precise data processing and analysis for decades. Researchers of humanities and social sciences are increasingly adopting computational tools such as artificial intelligence (AI) and machine learning (ML) to analyse human behaviour in society by identifying patterns within data. In this regard, this paper presents the modelling of teachers and students’ perceptions regarding gender bias in text books through AI. The data was collected from 470 respondents through a questionnaire using five different themes. The data was analysed with support vector machines (SVM), decision trees (DT), random forest (RF) and artificial neural networks (ANN). The experimental results show that the prediction of perceptions regarding gender varies according to the theme and leads to the different performances of the AI techniques. However, it is observed that when data from all the themes are combined, the best results are obtained. The experimental results show that ANN, on average, demonstrates the best performance by achieving an accuracy of 87.2%, followed by RF and SVM, which demonstrate an accuracy of 84% and 80%, respectively. This paper is significant in modelling human behaviour in society through AI, which is a significant contribution to the field.

Deception scholarship is becoming increasingly interested in knowing how findings located predominantly in the North American context travel over diverse cultural contexts. Feeding into this line of inquiry, the study predicted that people’s perception of deceptive communication is always commensurate with their cultural understanding of deception as moral evil or a social necessity. Furthermore, the study also proposed that the perceived deceptiveness of a deceitful statement is the function of the deception goal it sets out to achieve. To test this assumption for Pakistani culture, the study used the theoretical guidelines and experimental design proposed in Information Manipulation Theory (IMT). Using Buller and Burgoon’s typology of deception motives, three deception motives (i.e., instrumental, interpersonal and identity) were identified and situational prompts were created in each category. The participants ( N = 753) read the situational prompts and rated five different types of information manipulations on four 7-point semantic differential scales. The results indicated that the motive type had a significant effect on the perception of deceptive communication. The information manipulation carried out for instrumental purposes was rated more deceptive than the interpersonal and identity-based manipulations. Nevertheless, completely disclosive messages and falsifications were consistently rated the most honest and the most deceptive respectively. The results indicate that Pakistani culture places a high premium on the value of truth and treats indirect messages as less honest than completely truthful messages. The findings bring insights about an understudied collectivist culture and help to make empirical profiling of deceptive communication more robust.