•  
  •  
 

Scientific Information Research

Keywords

neural network; bullet screen; sentiment analysis; public opinion warning; food security

Abstract

[Purpose/significance]The negative public opinion warning system is constructed by sentiment of comments and bullet screen,which can analyze public opinion of food security and enhance the ability of food enterprises to respond to public opinion.[Method/process]ResNet method is used to link BERT model, BiGRU model,and feedforward neural network to construct the BERT-RGRU model,which can analyze the sentiment of bullet screen.The concept of "fake-neutral" is proposed to enhance sentiment analysis ability of the model.Method of "attention-weight" is used to process results of sentiment analysis model and calculate the value of early warning index,which can be used to determine whether there is a negative public opinion.[Result/conclusion]BERT-RGRU model performs well on the bullet screen testing data,F1-score is 2% higher than BERT model and at least 10% higher than traditional model like BiGRU.The public opinion early warning system also raises the alarm accurately in McDonald's real example.

First Page

33

Reference

[1] 曾润喜.网络舆情管控工作机制研究[J].图书情报工作，2009，53（18）：79-82.
[2] 孙晓宁，姚青.多元主题场景下的用户弹幕与评论特征比较研究：基于Bilibili网站[J].情报理论与实践，2021，44（09）：135-141.
[3] SEPP H，JÜRGEN S.Long Short-Term Memory[J].Neural Computation，1997，9（08）：1735-1780.
[4] KYUNGHYUN C，BART V M，CAGLAR G，et al.Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation[EB/OL].[2022-3-21].https：//arxiv.org/abs/1406.1078v3.
[5] 陶志勇，李小兵，刘影，等.基于双向长短时记忆网络的改进注意力短文本分类方法[J].数据分析与知识发现，2019，3（12）：21-29.
[6] GONCALVES S，CORTEZ P，MOROS.A deep learning classifier for sentence classification in biomedical and computer science abstracts[J].Neural Computing & Applications，2020，32（11）：6793-6807.
[7] HE K M，ZHANG X Y，REN S Q，et al.Deep Residual Learning for Image Recognition[EB/OL].[2022-3-21].https：//arxiv.org/abs/1512.03385.
[8] JACOB D，MING W C，KENTON L，et al.BERT：Pre-training of Deep Bidirectional Transformersfor Language Understanding[EB/OL].[2022-3-21].https：//arxiv.org/abs/1810.04805v2.
[9] LIU Y，OTT M，GOYAL N，et al. Roberta：A robustly optimized bert pretraining approach[EB/OL].[2022-4-4].https：//arxiv.org/abs/1907.11692v1.
[10] CUI Y M，CHE W X，LIU T，et al.Pre-Training With Whole Word Masking for Chinese BERT[J].IEEE-ACM Transactions on Audio Speech and Language Processing，2021，29：3504-3514.
[11] CUI Y M，CHE W X，LIU T，et al.Revisiting Pre-Trained Models for Chinese Natural Language Processing.[EB/OL].[2022-4-4].https：//arxiv.org/abs/2004.13922v2.
[12] 刘勘，李晶，刘萍.基于马尔可夫链的舆情热度趋势分析[J].计算机工程与应用，2011，47（36）：170-173.
[13] 吴鹏，应杨，沈思.基于双向长短期记忆模型的网民负面情感分类研究[J].情报学报，2018，37（08）：845-853.
[14] 黄立赫，石映昕.面向视频弹幕的网络舆情事件监测研究[J].情报杂志，2022，41（02）：146-154.
[15] 叶健，赵慧.基于大规模弹幕数据监听和情感分类的舆情分析模型[J].华东师范大学学报（自然科学版），2019（03）：86-100.
[16] 段炼.面向弹幕文本的情感分析研究[D].重庆：重庆邮电大学，2019.
[17] 李云龙.网络直播平台中弹幕的舆情分析研究[D].天津：天津理工大学，2020.
[18] 冉自春.ACG影响下的弹幕亚文化风格研究[D].兰州：兰州大学，2018.
[19] 甘春梅，梁栩彬，李婷婷.使用与满足视角下社交网络用户行为研究综述：基于国外54篇实证研究文献的内容分析[J].图书情报工作，2018，62（07）：134-143.
[20] 傅依娴，芦天亮，马泽良.基于One-Hot的CNN恶意代码检测技术[J].计算机应用与软件，2020，37（01）：304-308，333.
[21] TOMAS M，CHEN K，GREG C，et al.Efficient Estimation of Word Representations in Vector Space[EB/OL].[2022-3-21].https：//arxiv.org/abs//1301.3781.
[22] 李悦晨，钱玲飞，马静.基于BERT-RCNN模型的微博谣言早期检测研究[J].情报理论与实践，2021，44（07）：173-177，151.
[23] ZHANG S X，HU Z Y，ZHU G L，et al.Sentiment classification model for Chinese micro-blog comments based on key sentences extraction[J].Soft Computing，2021，25（01）：463-476.
[24] ABDI L，HASHEMI S.To combat multi-class imbalanced problems by means of over-sampling and boosting techniques[J].Soft Computing，2015，19（12）：3369-3385.
[25] BORDOLOI M，CHATTERJEE P C，BISWAS S K.et al.Keyword extraction using supervised cumulative TextRank[J].Multimedia Tools and Applications，2020，79（41）：31467-31496.

Download

Share

COinS