Title: Topic popularity prediction of online social network based on single objective evolution

Authors: Qingjie Meng

Addresses: Nanjing Institute of Industry Technology, Nanjing, 210023 China

Abstract: In order to overcome the problem that the prediction results of the existing topic heat prediction methods have large deviation, an online social network topic heat prediction method based on the single objective evolution method is proposed. This method uses the way of web crawler to obtain the network topic data, uses the principal component analysis method to calculate the weight of topic heat prediction index, obtains the expression of influence index, and constructs online through the single objective evolution method Social network topic heat prediction model framework, determine the model parameters, to achieve the prediction of topic heat. The experimental results show that the prediction method of online social network topic popularity guarantees that the deviation of prediction results is within 11.05, and the highest accuracy of trend prediction is 73.14, R2 of video prediction is equal to 0.92, which has better prediction effect.

Keywords: single objective evolution; online social network; topic popularity; web crawler; principal component analysis method.

DOI: 10.1504/IJAACS.2020.10032771

International Journal of Autonomous and Adaptive Communications Systems, 2020 Vol.13 No.4, pp.371 - 388

Received: 05 Nov 2019
Accepted: 01 Feb 2020

Published online: 12 Jan 2021 *

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