Analysis of the Influence of Algorithm Recommendation on the Dissemination Effect of Anti-Fraud Information in Social Networks

DOI: https://doi.org/10.62517/jbdc.202501118

Author(s)

Yutong Deng, Mengqi Zhao

Affiliation(s)

Department of Public Security Management, Beijing Police Academy, Beijing, China

Abstract

Telecommunication network fraud is a pressing societal issue, and social network platforms play a vital role in disseminating anti-fraud information. This study examines the impact of algorithmic recommendation systems on anti-fraud information dissemination, focusing on their potential to improve information coverage, user engagement, and educational effectiveness, while addressing their limitations. By combining theoretical analysis with empirical data, the research evaluates how algorithmic recommendations enhance information visibility and relevance through personalized data-push, while also identifying risks such as algorithmic opacity and misinformation diffusion. The findings indicate that algorithmic recommendations significantly improve the reach and accuracy of anti-fraud information but may inadvertently spread false information due to inherent biases. The study concludes that, despite these challenges, optimizing algorithms can effectively enhance anti-fraud information dissemination, thereby raising public awareness and personal protection capabilities. This research provides insights into the role of algorithms in social networks and suggests the need for improved regulatory and technical standards to ensure the ethical use of technology in combating fraud.

Keywords

Social Network; Algorithm Recommendation; Information Dissemination; Anti-Fraud Information; User Behavior

References

[1] Wang Li, Wan Yifan. Research on the algorithm of personalized media recommendation system based on deep learning. Radio and TV Information, 2024,31 (10): 109-112.doi: 10.16045/j. cnki.rti.2024.10.030. [2] Yu Guoze. Study on the communication strategy of short video-taking Tik Tok, the National Anti-Fraud Center, as an example. Collected and edited, 2024, (09):56-58. [3] Jiang Jialin, Ma Yifei. Building a new publicity system with algorithm recommendation as the core. News Sentinel, 2023, (03):20-22. [4] Sunstein C. Infotopia: How Many Minds Produce Knowledge. Oxford: Oxford University Press, 2006:9-10. [5] Qiu Chengcheng, Peng Xiangbin, Hu Chengming, et al. Study on the influencing factors and paths of users' emotional polarization under the information cocoon effect. Library Science Research, 2024, (07): 94-109. DOI: 10.15941/j.cnki.ISSN 1001-0424.2001 [6] Wu Bao. Challenges faced by mainstream ideological communication in the era of algorithm recommendation and its countermeasures. Journal of China Shiyou University (Social Science Edition), 2021, 37 (4): 98-104. [7] Zhang Cancan. The artificial public opinion manipulated by the algorithm is the natural enemy of the real world. Young reporter, 2022, (07): 111. doi: 10.15997/j. cnki.qnjz.2022.07.024. [8] Sun Yan. research on the influence of algorithm recommendation on the guiding power of mainstream media. southern medical university, 2024. doi: 10.27003/d.cnki.gojyu.20003.1000100001005 [9] Zhou Liangfa, Han Jianchen. Intelligent algorithm helps to make propaganda and ideological work precise. People's Forum, 2020, (34):49-51. [10] Ma Hongli. Algorithm recommendation has its own "regulations". information china, 2022, (01):45-48. [11] Xu Ke. Taming algorithms: the historical development and contemporary system of algorithmic governance. Journal of East China University of Political Science and Law, 2022 (1): 99-113