Internet rumor audience response prediction algorithm based on machine learning in big data environment

Tools

Yang, Suhong and Wang, Shenghui and Yiwen, Y. (2022) Internet rumor audience response prediction algorithm based on machine learning in big data environment. Wireless Communications and Mobile Computing, 2022. 3632679. ISSN 1530-8669 (https://doi.org/10.1155/2022/3632679)

[thumbnail of Yang-etal-WCMC-2022-Internet-rumor-audience-response-prediction-algorithm]
Preview
 Text. Filename: Yang_etal_WCMC_2022_Internet_rumor_audience_response_prediction_algorithm.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (610kB)| Preview

Abstract

Rumors are an important factor affecting social stability in some special times. Therefore, the dissemination and prevention and control mechanisms of rumors have always been issues of concern to the academic community and have long been highly valued and widely discussed by experts and scholars. However, in combination with the Internet as a new type of media, although people have begun to pay attention to online rumors, research on it is still relatively fragmented, especially in the cross-domain research specific to the social influence of online rumors, and there is no clear indication of online rumors. The specific definition also did not analyze in detail the internal connection between its influence and group behavior. Therefore, this article will combine actual cases to explore and analyze the spread and influence process of online rumors and show its social influence, hoping to enrich the research of online rumors. Nowadays, the Internet has become the most important carrier to reflect the public grievances. Internet users have expressed their opinions on hot issues such as enterprises, people’s livelihood, and government management, which has formed a powerful public opinion pressure, which has far exceeded the traditional media. The hidden dangers of security cannot be ignored. Therefore, how to monitor network public opinion from a large amount of network data is a difficult problem that needs to be solved urgently. Firstly, this consists of four modules: information collection, web page preprocessing, public opinion analysis, and public information report. Secondly, text clustering, the core technology of network public opinion, is optimized, and single-pass algorithm based on double threshold is proposed. Then the dual-threshold single-pass algorithm is optimized based on the MapReduce parallel computing model, and finally a network public opinion collection technology is formed under the background of big data. Simulation results can greatly improve the performance of text clustering and can effectively optimize the design using the parallel computing model based on MapReduce. The average miss rate after optimization is 0.7569 times, the average false alarm rate is 0.5556 times, and C det is 0.5714 times. It proves that the collection technology based on machine learning under the background of big data is effective and has good performance.

  • Item type:Article
    ID code:80649
    Dates:
    Date
    Event
    30 April 2022
    Published
    5 April 2022
    Accepted
    Subjects:Science > Mathematics > Computer software
    Department:UNSPECIFIED
    Depositing user: Pure Administrator
    Date deposited:10 May 2022 18:10
    Last modified:11 Nov 2024 13:29
    URI:https://strathprints.strath.ac.uk/id/eprint/80649
CORE (COnnecting REpositories)