Identifying Persian bots on Twitter; which feature is more important: Account Information or Tweet Contents?

Nowadays, Social media is heading toward personalization more and more. People express themselves and reveal their beliefs, interests, habits, and activities, simply giving a glimpse of their personality traits. The thing that pushed us toward further investigating the mutual relation between personality and social media, taking into consideration the shortage in covering such important topic, especially in rich morphological languages. In this paper, we work on the connection between usage of Arabic language on social outlets (mainly Facebook and Twitter) and personality traits. We indicate the personality traits of users based on the information extracted from their activities and the content of their posts/tweets in Social Networks. We use linguistic features, beside some other features like emoticons. We gathered personality data using Arabic personality test based on Myers-Briggs Type Indicator (MBTI), which contains Thinking, Feeling, Intuition, Introversion, Sensation, Extroversion, Perceiving and Judgement traits. We collected our dataset from 522 volunteers, who permitted us to crawl their tweets and posts in Twitter and Facebook. Analysis of this dataset proved that some linguistic features could be used to differentiate between different personality traits. We used and implemented Deep Learning, and BERT to reveal personality and create a model for this purpose. Up to our knowledge, this is the first work on detection of personality traits from social network’s data in Arabic language.