A Brainwave-based Attention Diagnosis and Music Recommendation System for Reading Improvement

Abstract

The sense of ‘Attention’ has a certain degree of influence on the effectiveness of learning. It was found that good music boosts reading interest. Music referral systems have been proactively explored using hybrid methods. In this work, first, a select electroencephalographic(EEG) was used to record and review attention according to the individual's choices for music material due to the introduction of an attention device. Then, the collected brainwave data values are filtered for invalid data and then combined with a Supper Vector Machine (SVM) classifier. SVM classifier for calculation and analysis identifies two types of brainwave data values (attention vs. non-attention). The recognition rate was up to 72%. We suggest a hybrid music recommendation model based upon an exciting device, which incorporates the user's electroencephalographic(EEG) information and records the individual's choices for music material due to the introduction of an attention device. The experimental outcomes reveal that the system, without a doubt, gives customers a personalized list of music, making them more attentive and continue reading.