Prediction of Weibo Negative Public Opinion Based on Grey-Weighted Markov Model

Authors

Chunlin DENG, Public Management College, Xiangtan University, Xiangtan 411105
Quanliu CHEN, Public Management College, Xiangtan University, Xiangtan 411105
Jianqi LI, Hunan City University, Yiyang 413000

Keywords

Grey-weighted Markov; weibo negative public opinion; public opinion heat forecast; user negative emotion

Abstract

[Purpose/significance]Combined with the weighted Markov and grey prediction model, the negative sentiment is introduced into the influencing factors of public opinion heat to construct the prediction model of Weibo negative public opinion heat, so as to optimize the model and enrich the public opinion monitoring system. The research results can provide relevant departments advance warning.[Method/Process]Taking Weibo social media users as the object, taking the "Hua Lala Incident" and "Dalian 522 Incident" as the research events, and processing the collected data, construct a grey-weighted Markov negative public opinion heat prediction Model.[Result/conclusion]The results show that the prediction model based on gray-weighted Markov is more accurate than the single gray prediction and residual modified gray prediction model, and can effectively predict the development of public opinion in emergencies.

First Page

78

Recommended Citation

DENG, Chunlin; CHEN, Quanliu; and LI, Jianqi (2023) "Prediction of Weibo Negative Public Opinion Based on Grey-Weighted Markov Model," Scientific Information Research: Vol. 5: Iss. 2, Article 7.
Available at: https://eng.kjqbyj.com/journal/vol5/iss2/7

Reference

[1] 中国互联网络信息中心.第49次《中国互联网络发展状况统计报告》[R/OL].（2022-02-25）[2022-05-10].http：//www.cnnic.cn/NMediaFile/old_attach/P020220721404263787858.pdf.
[2] 刘毅.网络舆情研究概论[M].天津：天津人民出版社，2007.
[3] 曾润喜，陈创.网络舆情信息传播动力机制的比较研究[J].图书情报工作，2018，62（07）：12-20.
[4] 任中杰，张鹏，兰月新，等.面向突发事件的网络用户画像情感分析：以天津“8·12”事故为例[J].情报杂志，2019，38（11）：126-133.
[5] 刘丛，谢耘耕，万旋傲.微博情绪与微博传播力的关系研究：基于24起公共事件相关微博的实证分析[J].新闻与传播研究，2015，22（09）：92-106，128.
[6] 邓建高，吴灵铭，齐佳音，等.基于信息关联的负面网络舆情风险分级与预测研究[J].情报科学，2022，40（01）：38-43.
[7] 冯兰萍，严雪，程铁军.重大突发事件微博舆情演化分析：以“天津大爆炸事故”为例[J].竞争情报，2021，17（03）：21-29.
[8] LI Q，DU Y J，LI Z Y，et al.HK-SEIR model of public opinion evolution based on communication factors[J].Engineering Applications of Artificial Intelligence，2021，100：104192.
[9] LIU X Y，TANG T，HE D B.Double-Layer Network Negative Public Opinion Information Propagation Modeling Based on Continuous-Time Markov Chain[J].The Computer Journal，2021，64（09）：1315-1325.
[10] 陈福集，肖鸿雁.基于改进ABC-BP模型的网络舆情热度预测研究[J].图书馆学研究，2018（09）：84-89，101.
[11] 牟冬梅，靳春妍，邵琦.基于情感分析的突发公共卫生事件网络舆情热度预测模型仿真[J].现代情报，2021，41（10）：59-66.
[12] ZHANG Y X，XU Z S，HAO Z N，et al.Dynamic assessment of Internet public opinions based on the probabilistic linguistic Bayesian network and Prospect theory[J].Applied Soft Computing，2021，106.
[13] YU N，LIU K，MA K.Analysis of Public Opinion Heat Trend in Universities on The Basis of Markov Chain[C]//2018 IEEE 15th International Conference on e-Business Engineering（ICEBE）.IEEE，2018：218-222.
[14] 王宁，赵胜洋，单晓红.基于灰色系统理论的网络舆情预测与分级方法研究[J].情报理论与实践，2019，42（02）：120-126.
[15] 连芷萱，兰月新，夏一雪，等.基于首发信息的微博舆情热度预测模型[J].情报科学，2018，36（09）：107-114.
[16] 彭艺，李磊.一种基于马尔可夫链的微信舆情热度预测模型[J].信息技术，2016（08）：81-84.
[17] 郑小平，高金吉，刘梦婷.事故预测理论与方法[M].北京：清华大学出版社，2009.
[18] 夏乐天，朱元甡.马尔可夫链预测方法的统计试验研究[J].水利学报，2007（S1）：372-378.
[19] 陈福集，史蕊.基于残差修正的多因素灰色模型的网络舆情预测研究[J].情报科学，2017，35（09）：131-135.
[20] 曾子明，黄城莺.基于BP神经网络的突发传染病舆情热度趋势预测模型研究[J].现代情报，2018，38（05）：37-44，52.
[21] 靖鸣，王敬云.突发公共事件中谣言对舆论监督影响研究：以新冠肺炎疫情事件为例[J].中国出版，2021（02）：49-53