Data shared on social networks can reflect numerous information about users, such as personality traits, inclinations, and interests. Consequently, research on predicting user personality from social network data has become increasingly focused. This study focuses on the Instagram application and is the first, to our knowledge, to examine Moroccan Instagram users. To study the effect of personality traits and gender on photo content, we predict and analyze the personalities of female and male Instagram users separately, based on characteristics extracted from the photos they share. This study is the first to predict the personality of both genders separately, given differences in the nature and preferences of genders. Additionally, we examine the effect of the number of images on prediction accuracy. Furthermore, three categories of features have been extracted from the images: visual, emotional, and content. Moreover, the Big Five model is used to represent users' personalities. Additionally, we collected a database of 316 Instagram users; it is the largest compared to previous works and includes users from different regions and social classes, which makes the results more generalizable. A root mean square error (RMSE) related to the [1,5] score scale was used to indicate prediction accuracy. In general, good results were obtained for all traits, with outperforming results in predicting consciousness for females (RMSE=0.59) and openness for males(RMSE=0.59), compared to previous studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.