Utilizing Machine Learning Algorithms Trained on AI-generated Synthetic Participant Recent Music-Listening Activity in Predicting Big Five Personality Traits

Abstract

The recent rise of publicly available artificial intelligence (AI) tools such as ChatGPT hasraised a plethora of questions among users and skeptics alike. One major question asks, "Has AIgained the ability to indistinguishably mimic the psychology of its organic, human counterpart?".Since music has been known to be a positive predictor of personality traits due to the individuality ofpersonal preference, in this paper we use machine learning (ML) algorithms to analyze thepredictability of AI-generated or 'synthetic' participants' Big 5 personality traits (Openness,Conscientiousness, Extraversion, Agreeableness, and Neuroticism) using their recent music listeningactivity and motivations for listening to music. Recent music listening history for syntheticparticipants is generated using ChatGPT and the corresponding audio features for the songs arederived via the Spotify Application Programming Interface (Beats per minute, Danceability,Instrumentals, Happiness, etc). This study will also administer the Uses of Music Inventory toaccount for synthetic participants’ motivations for listening to music: emotional, cognitive, andbackground. The dataset will be trained and tested on scaler-model combinations to identify thepredictions with the least mean absolute error using ML models such as Random Forest, DecisionTree, K-Nearest Neighbors, Logistic Regression, and Support Vector Machine. Both regression(continuous numeric value) and classification (Likert scale option) prediction methods will be used.An Exploratory Factor Analysis (EFA) will be conducted on the audio features to find a latentrepresentation of the dataset that machine learning is also trained and tested on. A full literaturereview showed this is the first study to use both Spotify API data, rather than self-reported musicpreference, and machine learning, in addition to traditional statistical tests and regression models, topredict the personality of a synthetic college student demographic. The findings of this study showChatGPT struggles to mimic the diverse and complex nature of human personality psychology andmusic taste. This paper is a pilot study to a broader ongoing investigation where the findings ofsynthetic participants are compared to that of real college students using the same inventories forwhich data collection is ongoing.