An Integrated Model Combining Grey Methods and Neural Networks and its Application to Burst Topic Tendency Prediction

Date

2020

Advisors

Journal Title

Journal ISSN

ISSN

0957-3720

DOI

Volume Title

Publisher

Research Information Ltd

Type

Article

Peer reviewed

Yes

Abstract

Studying the development tendency of topics is an important part of online social network (OSN) analysis. To solve the problem of ad hoc topic popularity tendency prediction under insufficient effective samples, data sparsity and low accuracy of the prediction model, this study combines grey system theory with neural network method to propose a new model for topic tendency prediction. In this study, the grey relational analysis method is used to construct the social network topic popularity evaluation index system, and the topic popularity tendency is classified and weighted based on the grey proximity, and then the integrated system combining GM(1,1) model with BP neural network (BP-NN) model is established. Taking Sina Weibo’s burst topic data as an example, the effectiveness of the proposed model is verified. The experimental results show that the fusion model of proposed integrated model is better than a single independent prediction model, which can be effectively used to predict the trend of the popularity of a social network topic.

Description

The file attached to this record is the author's final peer reviewed version.

Keywords

Sudden Topic, Grey System, BP-NN, Prediction Model

Citation

Hong, Y., Zhang Q., Yang, Y. and Wu, L. (2020) An integrated model combining grey methods and neural networks and its application to burst topic tendency prediction. Journal of Grey System,

Rights

Research Institute