Sentiment Analysis Algorithm Based on Dance Rhythmic and Melodic Features

Zhe Chen

doi:10.4108/eetsis.4729

Authors

Zhe Chen Dance Academy, Shandong Art Institute

DOI:

https://doi.org/10.4108/eetsis.4729

Keywords:

dance rhythm, melodic characteristics, sentiment psychology, analysis algorithm

Abstract

INTRODUCTION: Dance is not only able to strengthen the body but also an expression of art. It can not only express the culture of a nation or a country but also express the emotions of a country. Therefore, it is essential to utilize algorithms for the study of dance rhythm and melodic characteristics in today's world, and introduces a sentiment analysis algorithm for the study.
OBJECTIVES: To disseminate our traditional dance culture, carry forward the spirit of our traditional art, enhance the creative level of our dance art, improve the current dance art in our country can not better apply the algorithm, and solve the problem that our current sentiment analysis algorithm can not be combined with art disciplines.
METHODS: Use the neural network and deep learning in sentiment analysis to establish a sentiment analysis algorithm adapted; then use the sentiment analysis algorithm to calculate the in-depth filtering of the dance rhythm and melodic characteristics of the research object; finally, the heat map of the dance rhythm and melodic characteristics of the SRD is calculated according to the experiment of the algorithm.
RESULTS: The core influencing factors of dance rhythm and melodic features are found to be attention mechanism and LMT through heat analysis (knowledge map); the experimental results using the sentiment analysis algorithm can be found to have a significant mediating effect on the joint enhancement of dance rhythm and melodic sense.
CONCLUSION: The development of dance art not only lies in communication and integration but also combination with contemporary computer technology; using sentiment analysis algorithms can better analyze the dance rhythm and melodic characteristics; therefore, the level of algorithm application in the field of dance art should be improved.

References

Bonastre, C., & Timmers, R. (2021). Comparison of beliefs about teaching and learning of emotional expression in music performance between Spanish and English HE students of music. SAGE Publications, 1(1), 45–71.

Crone, C. L., Rigoli, L. M., Patil, G., Pini, S., & Richardson, M. J. (2021). Synchronous vs. non-synchronous imitation: Using Dance to explore interpersonal coordination during observational learning. Human Movement Science, 76(1), 102776.

He, Z., Dumdumaya, C. E., & Machica, I. K. D. (2023). Text Sentiment Analysis Based on Multi-Layer Bi-Directional LSTM with a Trapezoidal Structure. Computer, 7, 639–654.

Leslie-Spinks, J. (2022). “How can we know the dancer from the dance?” Perspectives on Musicality in Human Movement. Dance Research, 40(1), 85–103. https://doi.org/10.3366/drs.2022.0359

Liu, X., & Hu, J. (2021). Dance Movement Recognition Technology Based on Multi-feature Information Fusion. Hindawi, 23(23), 133–164.

Lovera, F., Cardinale, Y. C., & Homsi, M. N. (2021). Sentiment Analysis in Twitter Based on Knowledge Graph and Deep Learning Classification. Electronics, 56, 74–101. https://doi.org/10.3390/electronics10222739

Ma, G. X., Born, M. P., Petrou, P., & Bakker, A. B. (2021). Bright sides of dark personality? A cross‐cultural study on the dark triad and work outcomes. International Journal of Selection and Assessment, 29(3–4), 510–518. https://doi.org/10.1111/ijsa.12342

Milne, M. J., & Neely, K. C. (2022). Exploring female dancer’s emotions and coping experiences following deselection: An interpretative phenomenological analysis. Psychology of Sport and Exercise, 14(13), 241–179. https://doi.org/10.1016/j.psychsport.2022.102289

Otterbein, R., Jochum, E., Overholt, D., Bai, S., & Dalsgaard, A. (2022). Dance and Movement-Led Research for Designing and Evaluating Wearable Human-Computer Interfaces. Proceedings of the 8th International Conference on Movement and Computing, 121(121), 111–154.

Park, S. H. (2021). A Study on the Dance as professional expertise and labour. Dance Research Journal of Dance, 45(45), 271–299. https://doi.org/10.21317/ksd.79.3.7

Reiser, V. (2021). A Kinesiological Analysis of Dancers at the University of Nebraska-Lincoln. 23(23), 90–141.

Setyawan, A. B., Prihatini, N. S., Rochana, W. S., & Soewardikoen, D. W. (2021). Regional Branding: Transfers Medium Dance into Visual Identity in Ponorogo Image Construction. Rupkatha Journal on Interdisciplinary Studies in Humanities, 1(1), 48–82. https://doi.org/10.21659/rupkatha.v13n1.07

Soheil, M. A. (2021). The integrity of the Cultural Landscape of Persepolis. Change over Time, 2, 10. https://doi.org/10.1353/cot.2021.0007

Stock, C. (2022). Training the Thinking Dancer: Creating Careers in Dance in the 21st Century. 15(15), 44–95.

Taryana, T., Budiman, A., Karyati, D., & Julia, J. (2021). Enhancing Students’ Understanding and Skills on Dance Music: An Action Research. Cypriot Journal of Educational Sciences, 16(16), 29–41. https://doi.org/10.18844/cjes.v16i5.6334

Wasti, S. A., Aydin, C., Altunsu, B., & Beyhan, T. B. (2021). Recalling Positive and Negative Events: A Cross-Cultural Investigation of the Functions of Work-Related Memories. Journal of Applied Research in Memory and Cognition, 23, 56–93. https://doi.org/10.1016/j.jarmac.2020.10.001

Yoo, G. J., & Lee, G. (2021). Seeking directions for parental education programs through sentiment analysis based on text mining: Centered on the play. Journal of Children's Literature and Education, 34, 281–350. https://doi.org/10.22154/JCLE.22.4.9

Yue, L. (2021). Emotional Expression and Artistic Reconstruction in Musical Performance. Modern Education, 005(007), P.112-115.

Zhai, X. (2021). Dance Movement Recognition Based on Feature Expression and Attribute Mining. Complexity, 2021(21), 1–12.

Zhang, L., Wu, Y., Chu, Q., Li, P., Wang, G., Zhang, W., Qiu, Y., & Li, Y. (2023). SA-Model: Multi-Feature Fusion Poetic Sentiment Analysis Based on a Hybrid Word Vector Model. Computer Model, 56(56), 177–202.

Yu Shoujian, Wang Baoying & Lu Na. (2022). Sentiment Lexicon Construction Based on Improved Left-Right Entropy Algorithm. Donghua Journal, 001, 039.