大数据 ›› 2022, Vol. 8 ›› Issue (5): 124-138.doi: 10.11959/j.issn.2096-0271.2022034

• 研究 • 上一篇    

基于时间编码LSTM的高校舆情热点趋势预测研究

易杰1, 曹腾飞1, 黄明峰2, 黄肖翰1, 张子震1   

  1. 1 青海大学计算机技术与应用系,青海 西宁 810016
    2 云上贵州大数据产业发展有限公司,贵州 贵阳 550081
  • 出版日期:2022-09-01 发布日期:2022-09-01
  • 作者简介:易杰(1998- ),男,青海大学计算机技术与应用系硕士生,主要研究方向为深度学习、数据挖掘
    曹腾飞(1987- ),男,博士,青海大学计算机技术与应用系副教授,中国计算机学会会员,主要研究方向为舆情分析、服务推荐与管理
    黄明峰(1977- ),男,清华大学创新领军工程博士生,云上贵州大数据产业发展有限公司研究员级高级工程师,主要研究方向数据治理、大数据应用、数据可信流通
    黄肖翰(1999- ),男,青海大学计算机技术与应用系硕士生,主要研究方向为深度学习、数据挖掘
    张子震(1994- ),男,青海大学计算机技术与应用系硕士生,主要研究方向为强化学习、舆情分析
  • 基金资助:
    国家自然科学基金资助项目(62101299);青海省自然科学基金资助项目(2020-ZJ-943Q);青海大学党建与思想政治教育研究项目(szzx2012)

Research on trend prediction of time-coded LSTM based public opinion hot spots in universities

Jie YI1, Tengfei CAO1, Mingfeng HUANG2, Xiaohan HUANG1, Zizhen ZHANG1   

  1. 1 Department of Computer Technology and Applications, Qinghai University, Xining 810016, China
    2 Guizhou-Cloud Big Data Industry Development Co., Ltd., Guiyang 550081, China
  • Online:2022-09-01 Published:2022-09-01
  • Supported by:
    The National Natural Science Foundation of China(62101299);The Natural Science Foundation of Qinghai Province(2020-ZJ-943Q);Qinghai University Party Building and Ideological and Political Education Research Project(szzx2012)

摘要:

随着互联网技术的发展,网络舆情热点信息能在短时间内迅速传播。预测舆情热点的发展趋势,有助于高校对学生思想健康状况进行分析管理,也是当下网络舆情信息研究领域的重要课题。针对微博中的舆情信息文本,构建基于时间编码长短期记忆网络(LSTM)的高校舆情热点趋势预测模型,并与支持向量机、循环神经网络两种模型的预测效果进行对比,验证了基于时间编码的LSTM算法在舆情趋势预测上的准确率。最后,利用微博中的高校实时舆情事件对构建的模型预测效果进行评估,并动态调整评估参数,实现了对评估性能的优化,预测效果得到了显著提升。

关键词: 长短期记忆网络, 热点预测, 高校舆情, 时序数据, 时间编码

Abstract:

With the development of Internet technology, network public opinion hot information can be quickly spread in a short time.Predicting the development trend of public opinion hot spots is helpful to the analysis and management of college students’ ideological health, and it is also an important issue in the field of network public opinion information research.Aiming at the public opinion information text in microblog, the hot spots trend prediction model of universities based on time-coded long short-term memory (LSTM) was constructed.Compared with the prediction effect of support vector machine, and recurrent neural network through experiments, the superiority of time-coded LSTM was verified.Finally, the prediction effect of time-coded LSTM was evaluated by using the real-time public opinion events of colleges and universities in microblogs, and the evaluation parameters were dynamically adjusted to optimize the performance of the evaluation, and the prediction effect was improved significantly.

Key words: LSTM, hot spots prediction, public opinion in universities, time series data, time-coded

中图分类号: 

No Suggested Reading articles found!