In this paper, firstly, on the basis of cognitive mapping, music data are processed in four directions, namely, sound spectrum extraction, audio superposition, audio tempo, and tone intensity adjustment, and then audio sequences are sliced and diced, so that the cognitive mapping can be more focused on capturing localized useful information. Then, the BERT model is used to encode the music sequences so that the output music sequences already contain aesthetic and emotional features and the cognitive mapping-based music emotion analysis model is constructed according to the music emotion learning layer, the emotion feature aggregation layer, and the full connectivity layer, and analyzes the aesthetic value of music education in colleges and universities. According to the results, the BERT model had a difference of 0.13% on the MED dataset and 0.03% on the MTD dataset. On the mean value of the aesthetic value of traditional music, introverted personality (3.61) was higher than extroverted personality (3.52). This study has a positive effect on the cultivation of aesthetic value in music education in colleges and universities and proposes effective ways to enhance aesthetic value in college and university music teaching.