Title: Feature extraction of news communication on Microblog platform based on multilevel sliding window model

Authors: Cheng Cui

Addresses: Finance and Asset Management Office of Shijiazhuang University of Applied Technology, Shijiazhuang, 050081, China

Abstract: In order to fully understand the characteristics of news dissemination on Microblog platforms, this article proposes a method for extracting news dissemination features on Microblog platforms based on a multi-level sliding window model. Firstly, identify the four major characteristics of Microblog platform news, including high timeliness, free writing style, rich personal emotional bias, and the ability to restore the truth of the news. Secondly, a Microblog platform news communication representation model is constructed using the news communication theme content as input and the Microblog platform news communication representation vector as output. Finally, determine the multi-level sliding window counter, correspond to the sub window positions, and segment the feature data to complete the feature extraction of news dissemination on Microblog platform. The experimental results show that the proposed method has a high recall rate for feature extraction and good feature data balance.

Keywords: multilevel sliding window model; Microblog platform; news dissemination; feature extraction.

DOI: 10.1504/IJWBC.2024.142483

International Journal of Web Based Communities, 2024 Vol.20 No.3/4, pp.212 - 227

Received: 17 May 2023
Accepted: 10 Oct 2023
Published online: 04 Nov 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article