Prediction Model of Music Popular Trend Based on NNS and DM Technology
The popular trend of today’s music can be obtained by deep excavation, analysis, and prediction of the audience’s preferences. Using huge music library resources and user behavior to form music big data and truly realizing the aggregation of audience preferences determine the popular development tre...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Function Spaces |
| Online Access: | http://dx.doi.org/10.1155/2022/6104056 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849467325439279104 |
|---|---|
| author | Yichen Xu Mingxun Wang Hao Chen Fan Hu |
| author_facet | Yichen Xu Mingxun Wang Hao Chen Fan Hu |
| author_sort | Yichen Xu |
| collection | DOAJ |
| description | The popular trend of today’s music can be obtained by deep excavation, analysis, and prediction of the audience’s preferences. Using huge music library resources and user behavior to form music big data and truly realizing the aggregation of audience preferences determine the popular development trend of music. Therefore, this paper will apply data mining (DM) technology, introduce neural network (NNS) theory, establish a prediction model of music fashion trend, predict and evaluate the music fashion trend according to the selected evaluation index, find the change of music fashion trend in time, and provide decision-making basis for music fashion trend. In this paper, the prediction of music popularity trend based on NNS and DM technology is studied. In the prediction of the number of songs played by 10 artists, the NNS algorithm proposed in this paper reduces the prediction effect from the original 0.074 and 0.045 to 0.044 and 0.032, respectively, and the error rates are reduced by 35.7% and 29.4%, respectively, compared with the learning algorithm and the decision tree algorithm. Among the three methods, the NNS algorithm in this paper has the highest accuracy. Therefore, it can be proved that the model proposed in this paper is more suitable for predicting the trend of music popularity. In the end, it can accurately control the trend of pop music and also realize the aggregation of user preferences to determine the trend of pop music. |
| format | Article |
| id | doaj-art-de84167d070a4e2f81fdbd48e5a41bfa |
| institution | Kabale University |
| issn | 2314-8888 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Function Spaces |
| spelling | doaj-art-de84167d070a4e2f81fdbd48e5a41bfa2025-08-20T03:26:16ZengWileyJournal of Function Spaces2314-88882022-01-01202210.1155/2022/6104056Prediction Model of Music Popular Trend Based on NNS and DM TechnologyYichen Xu0Mingxun Wang1Hao Chen2Fan Hu3College of Air Services and MusicCollege of Air Services and MusicSchool of Information EngineeringCollege of Science and TechnologyThe popular trend of today’s music can be obtained by deep excavation, analysis, and prediction of the audience’s preferences. Using huge music library resources and user behavior to form music big data and truly realizing the aggregation of audience preferences determine the popular development trend of music. Therefore, this paper will apply data mining (DM) technology, introduce neural network (NNS) theory, establish a prediction model of music fashion trend, predict and evaluate the music fashion trend according to the selected evaluation index, find the change of music fashion trend in time, and provide decision-making basis for music fashion trend. In this paper, the prediction of music popularity trend based on NNS and DM technology is studied. In the prediction of the number of songs played by 10 artists, the NNS algorithm proposed in this paper reduces the prediction effect from the original 0.074 and 0.045 to 0.044 and 0.032, respectively, and the error rates are reduced by 35.7% and 29.4%, respectively, compared with the learning algorithm and the decision tree algorithm. Among the three methods, the NNS algorithm in this paper has the highest accuracy. Therefore, it can be proved that the model proposed in this paper is more suitable for predicting the trend of music popularity. In the end, it can accurately control the trend of pop music and also realize the aggregation of user preferences to determine the trend of pop music.http://dx.doi.org/10.1155/2022/6104056 |
| spellingShingle | Yichen Xu Mingxun Wang Hao Chen Fan Hu Prediction Model of Music Popular Trend Based on NNS and DM Technology Journal of Function Spaces |
| title | Prediction Model of Music Popular Trend Based on NNS and DM Technology |
| title_full | Prediction Model of Music Popular Trend Based on NNS and DM Technology |
| title_fullStr | Prediction Model of Music Popular Trend Based on NNS and DM Technology |
| title_full_unstemmed | Prediction Model of Music Popular Trend Based on NNS and DM Technology |
| title_short | Prediction Model of Music Popular Trend Based on NNS and DM Technology |
| title_sort | prediction model of music popular trend based on nns and dm technology |
| url | http://dx.doi.org/10.1155/2022/6104056 |
| work_keys_str_mv | AT yichenxu predictionmodelofmusicpopulartrendbasedonnnsanddmtechnology AT mingxunwang predictionmodelofmusicpopulartrendbasedonnnsanddmtechnology AT haochen predictionmodelofmusicpopulartrendbasedonnnsanddmtechnology AT fanhu predictionmodelofmusicpopulartrendbasedonnnsanddmtechnology |