Welcome to the InfoSci Platform
Reference Hub2
Prediction of Hot Topics of Agricultural Public Opinion Based on Attention Mechanism LSTM Model

Prediction of Hot Topics of Agricultural Public Opinion Based on Attention Mechanism LSTM Model

Lifang Fu, Feifei Zhao
Copyright: © 2021 |Volume: 12 |Issue: 4 |Pages: 16
ISSN: 1947-3192|EISSN: 1947-3206|EISBN13: 9781799861614|DOI: 10.4018/IJAEIS.289429
Cite Article Cite Article

MLA

Fu, Lifang, and Feifei Zhao. "Prediction of Hot Topics of Agricultural Public Opinion Based on Attention Mechanism LSTM Model." IJAEIS vol.12, no.4 2021: pp.1-16. http://doi.org/10.4018/IJAEIS.289429

APA

Fu, L. & Zhao, F. (2021). Prediction of Hot Topics of Agricultural Public Opinion Based on Attention Mechanism LSTM Model. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 12(4), 1-16. http://doi.org/10.4018/IJAEIS.289429

Chicago

Fu, Lifang, and Feifei Zhao. "Prediction of Hot Topics of Agricultural Public Opinion Based on Attention Mechanism LSTM Model," International Journal of Agricultural and Environmental Information Systems (IJAEIS) 12, no.4: 1-16. http://doi.org/10.4018/IJAEIS.289429

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In order to timely and accurately analyze the focus and appeal of public opinion on the Internet, A LSTM-ATTN model was proposed to extract the hot topics and predict their changing trend based on tens of thousands of news and commentary messages. First, an improved LDA model was used to extract hot words and classify the hot topics. Aimed to more accurately describe the detailed characteristics and long-term trend of topic popularity, a prediction model is proposed based on attention mechanism Long Short-Term Memory (LSTM) network, which named LSTM-ATTN model. A large number of numerical experiments were carried out using the public opinion information of "African classical swine fever" event in China. According to results of evaluation indexes, the relative superiority of LSTM-ATTN model was demonstrated. It can capture and reflect the inherent characteristics and periodic fluctuations of the agricultural public opinion information. Also, it has higher convergence efficiency and prediction accuracy.