Welcome to Francis Academic Press

The Frontiers of Society, Science and Technology, 2024, 6(11); doi: 10.25236/FSST.2024.061103.

Research on Audience Behavior Pattern Recognition and Prediction Based on Big Data Analysis

Author(s)

Zian Xu

Corresponding Author:
Zian Xu
Affiliation(s)

Television School, Communication University of China, Beijing, 100024, China

Abstract

The era of big data brings new opportunities for audience behavior pattern identification and prediction. This study applies big data analytics methods, such as machine learning and deep learning, to dig deeper into viewer behavior patterns and improve the accuracy of personalized recommendations. A prediction model based on time series analysis is designed, and the value of big data methods in precision marketing and service optimization is confirmed through evaluation and optimization. Meanwhile, the study faces challenges such as data privacy, quality and model generalization. Taken together, this study provides new perspectives on theory and application, and looks forward to a promising future for the application of big data in audience behavior research.

Keywords

big data; audience behavior patterns; predictive models; personalized recommendation

Cite This Paper

Zian Xu. Research on Audience Behavior Pattern Recognition and Prediction Based on Big Data Analysis. The Frontiers of Society, Science and Technology (2024), Vol. 6, Issue 11: 15-20. https://doi.org/10.25236/FSST.2024.061103.

References

[1] Zhao Hongtian. How big data portrays enterprise users[J]. Business (Review),2020(4):32-37.

[2] Fabio Nelli (original), Du Chunxiao (translation). Python data analytics [M]. Beijing: People's Posts and Telecommunications Press, 2019. 

[3] Sagiroglu S, Sinanc D. Big data: A review[C]//2013 international conference on collaboration technologies and systems (CTS). IEEE, 2013: 42-47.

[4] Oussous A, Benjelloun F Z, Lahcen A A, et al. Big Data technologies: A survey[J]. Journal of King Saud University-Computer and Information Sciences, 2018, 30(4): 431-448.

[5] Wang P, Sun Y, Meng W, et al. The method of how to predict weibo users’ recovery experience on the weekend based on weibo big data[J]. IEEE Access, 2020, 8: 194072-194081.

[6] ZHANG Yanfeng, LIU Min. Research on the Mechanism of Digital Hoarding Behavior of Mobile Social Media Users from the Perspective of Phenomenological Graph Analysis[J]. Modern Intelligence, 2024, 44(7):3-12+73.

[7] Liu Chun. Research on online learning behavior analysis model based on big data environment[J]. China New Technology and New Products,2023(23):28-30.

[8] Zeng Yuchu. Research on the influence model of social media users' usage behavior--Taking Shanghai cultural and creative industry park as an example[J]. China Media Technology,2023(8):77-80.

[9] Brian P. Watson, Feng Xixi. Tom Davenport Jeanne Harris Information for this[J]. Information Strategy, 2010(14):28-31.

[10] Chang Huijun, Shan Hong, Man Yi, Mao Mao. User behavior analysis based on time series decomposition [J]. Data Acquisition and Processing,2015,30(2):441-451.