Feature Analysis for Computational Personality Recognition Using YouTube Personality Data set

Abstract

It is an important yet challenging task to develop an intelligent system in a way that it automatically classifies human personality traits. Automatic classification of human traits requires the knowledge of significant attributes and features that contribute to the prediction of a given trait. Motivated by the fact that detection of significant features is an essential part of a personality recognition system, we present in this paper an in-depth analysis of audio visual, text, demographic and sentiment features for classification of multi-modal personality traits namely, extraversion, agreeableness, conscientiousness, emotional stability and openness to experience. We use the YouTube personality data set and use logistic regression model with a ridge estimator for the classification purpose. We experiment with audio-visual features, bag of word features, sentiment based and demographic features. Our results provide important insights about the significance of different feature types for personality classification task.