Dreams Through the Lens of AI: Comparative Insights into Emotion Prediction

Gradient Boosting outperforms Random Forest, Support Vector Machines, and Neural Networks in predicting emotions such as happiness, sadness, fear, and anger from dream reports. Using a dataset of 5,000 labeled dream reports, the models were evaluated on accuracy, precision, recall, F1-score, and AUC-ROC. Gradient Boosting achieved the highest accuracy and AUC-ROC values, making it the most effective model for emotion prediction in dreams. The findings indicate that AI can offer insights into the subconscious mind and has potential applications in psychology and mental health.

Study at a glance

Abstract

Abstract This paper explores the application of Artificial Intelligence (AI) in predicting emotions derived from dreams, a challenging task due to the complex and subjective nature of dreams. Emotions such as happiness, sadness, fear, and anger are often embedded in dream narratives, and predicting these emotional states can offer insights into the subconscious mind [1]. We compare four machine learning algorithms—Random Forest, Support Vector Machines (SVM), Neural Networks, and Gradient Boosting—using a dataset of 5,000 labeled dream reports. The models are evaluated based on several performance metrics, including accuracy, precision, recall, F1-score, and AUC-ROC. Results indicate that Gradient Boosting outperforms the other algorithms, providing the highest accuracy and AUC-ROC values, making it the most effective model for emotion prediction in dreams. This study highlights the potential of AI in advancing the understanding of dreams and emotional states, with applications in psychology and mental health. Keywords Dreams, Emotion Prediction, Artificial Intelligence, Machine Learning, Comparative Analysis