Multilingual Transformer-Based Personality Traits Estimation

Intelligent agents have the potential to understand personality traits of human beings because of their every day interaction with us. The assessment of our psychological traits is a useful tool when we require them to simulate empathy. Since the creation of social media platforms, numerous studies dealt with measuring personality traits by gathering users&#8217; information from their social media profiles. Real world applications showed how natural language processing combined with supervised machine learning algorithms are effective in this field. These applications have some limitations such as focusing on English text only and not considering polysemy in text. In this paper, we propose a multilingual model that handles polysemy by analyzing sentences as a semantic ensemble of interconnected words. The proposed approach processes <i>Facebook</i> posts from the <i>myPersonality</i> dataset and it turns them into a high-dimensional array of features, which are then exploited by a deep neural network architecture based on transformer to perform regression. We prove the effectiveness of our work by comparing the mean squared error of our model with existing baselines and the Kullback&#8722;Leibler divergence between the relative data distributions. We obtained state-of-the-art results in personality traits estimation from social media posts for all five personality traits.

Abstract licence: CC BY

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.