Knowledge of words: An interpretable approach for personality recognition from social media

摘要

Personality is one of the fundamental and stable individual characteristics that can be detected from human behavioral data. With the rise of social media, increasing attention has been paid to the ability to recognize personality traits by analyzing the contents of user-generated text. Existing studies have used general psychological lexicons or machine learning, and even deep learning models, to predict personality, but their performance has been relatively poor or they have lacked the ability to interpret personality. In this paper, we present a novel interpretable personality recognition model based on a personality lexicon. First, we use word embedding techniques and prior-knowledge lexicons to automatically construct a Chinese semantic lexicon suitable for personality analysis. Based on this personality lexicon, we analyze the correlations between personality traits and semantic categories of words, and extract the semantic features of users’ microblogs to construct personality recognition models using classification algorithms. Extensive experiments are conducted to demonstrate that the proposed model can achieve significantly better performances compared to previous approaches.