Deep learning models predict music enjoyment using EEG data

Researchers have developed deep learning models to predict music enjoyment using electroencephalography (EEG) data. Six models were compared, with DeepConvNet, CNN-LSTM, and GNN-CNN achieving the lowest mean absolute error. The temporal convolutional network (TCN) showed the highest correlation with listener ratings. Explainability analysis was used to identify key temporal segments influencing the TCN's predictions, providing a benchmark for EEG-based enjoyment regression. AI

IMPACT This research could lead to more objective measures of subjective experiences like music enjoyment, potentially impacting fields like personalized media recommendations and therapeutic applications.

RANK_REASON The item is an academic paper detailing a new methodology and benchmark for predicting music enjoyment using deep learning and EEG data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• DeepConvNet
• electroencephalography
• GNN-CNN
• Gotit.pub
• Hugging Face
• IArxiv
• Musin Grob
• ScienceCast
• TCN

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →