基于深度学习的医患舆情多维演化仿真分析

doi:10.3778/j.issn.1002-8331.2206-0167

摘要/Abstract

摘要： 为了探析医患关系近年来的情感演化过程，助力政府部门决策干预提供理论依据，从而更好引导网络舆论走向，促进和谐医患关系的构建。针对互联网复杂语境下大规模医患舆情文本数据，在BERT预训练模型下游任务中构建情感分类器，并与LDA主题抽取技术相结合进行多维情感演化仿真分析，最后结合ARIMA模型进行情感走势预测。通过实验分析表明，LDA-BERT医患舆情多维情感分析模型的情感预测准确度达到98%，ARIMA医患舆情时间序列预测模型的预测平均误差低于11.25%，证明其能够有效运用于大规模医患舆情演化的多维度监测与分析。

关键词: 医患舆情, LDA-BERT模型, ARIMA模型, 情感演化

Abstract: It can better guide the trend of network public opinion and improve the relationship between doctors and patients by analyzing the sentiment evolutionary trends of doctor-patient relationships in recent years and assisting the government in providing the theoretical basis for decision-making and intervention. In the large-scale public opinion text of doctors and patients in the complex context of the Internet, it has constructed a sentiment classifier in the downstream tasks of the pre-training model BERT. It is combined with LDA topic extraction technology for multi-dimensional emotional evolution analysis. Finally, the ARIMA model is combined to predict sentiment trends. The experimental results show that the sentiment prediction model accuracy based on LDA-BERT reaches 98%. The average prediction error of the ARIMA time series prediction of the doctor-patient public opinion model is less than 11.25%. It is demonstrated that the algorithm presented in this research can be effectively applied to the multi-dimensional monitoring and analysis of large-scale doctor-patient public opinion evolution.

Key words: doctor-patient public opinion, LDA-BERT model, ARIMA model, sentiment evolution

谭旭, 吴璞, 蒋知义, 邹凯, 吕欣. 基于深度学习的医患舆情多维演化仿真分析[J]. 计算机工程与应用, 2023, 59(19): 82-91.

TAN Xu, WU Pu, JIANG Zhiyi, ZOU Kai, LYU Xin. Research on Multi-Dimensional Evolution Model of Doctor-Patient Public Opinion Based on Deep Learning[J]. Computer Engineering and Applications, 2023, 59(19): 82-91.

参考文献

[1] 新华社.中华人民共和国国民经济和社会发展第十四个五年规划和2035年远景目标纲要[EB/OL].（2021-03-13）[2021-07-13].http：//www.gov.cn/xinwen/2021-03/13/content_5592681.htm.
The Xinhua News Agency.Outline of the 14th five-year plan for national economic and social development and vision 2035 of the PRC[EB/OL].（2021-03-13）[2021-07-13].http：//www.gov.cn/xinwen/2021-03/13/content_5592681.htm.
[2] 中国医师协会.中国医师执业状况白皮书[EB/OL].（2018-01-09）[2021-05-20].http：//www.cmda.net/zlwqgzdt/596.jhtml.
The Chinese Medical Doctor Association.White paper of practice status of Chinese doctors[EB/OL].（2018-01-09）[2021-05-20].http：//www.cmda.net/zlwqgzdt/596.jhtml.
[3] 中国互联网络信息中心.第47次中国互联网络发展状况统计报告[EB/OL].（2021-02-03）[2021-05-20].http：//www.cnnic.net.cn/hlwfzyj/hlwxzbg/hlwtjbg/202102/t20210203_71361.htm.
China Internet Network Information Center.The 47th statistical report on Internet development in China[EB/OL].（2021-02-03）[2021-05-20].http：//www.cnnic.net.cn/hlwfzyj/hlwxzbg/hlwtjbg/202102/t20210203_71361.htm.
[4] 孟祥伟，王澜，吴群红，等.多维视角下和谐医患关系构建[J].中国公共卫生，2020，36（8）：1163-1166.
MENG X W，WANG L，WU Q H，et al.Establishment of harmonious doctor-patient relationship under multidimensional perspectives：a cross-sectional study[J].Chinese Journal of Public Health，2020，36（8）：1163-1166.
[5] 李文芬，杨风，罗光强，等.基于PEST模型构建和谐医患关系的策略研究[J].中国卫生事业管理，2021，38（4）：254-255.
LI W F，YANG F，LUO G Q，et al.Research on the strategy toconstruct harmonious doctor-patient relationship based on PEST model[J].Chinese Health Service Management，2021，38（4）：254-255.
[6] 王璐，董琳，陈明雁，等.融媒体时代医院网络舆情管理模式探索[J].中国医院，2021，25（5）：87-88.
WANG L，DONG L，CHEN M Y，et al.A preliminary study on hospitals’ management mode of internet public opinion in the era of media convergence[J].Chinese Hospitals，2021，25（5）：87-88.
[7] 王士强.新媒体环境下医院舆情管理SWOT分析及对策[J].传媒，2020（17）：93-96.
WANG S Q.Hospital public opinion management under the new media environment based on SWOT model[J].Media，2020（17）：93-96.
[8] 曹博林.互联网医疗：线上医患交流模式、效果及影响机制[J].深圳大学学报（人文社会科学版），2021，38（1）：119-130.
CAO B L.Internet-based medical treatment：online doctor-patient communication，effect and influence[J].Journal of Shenzhen University（Humanities and Social Sciences），2021，38（1）：119-130.
[9] 顾秋阳，琚春华，鲍福光.融入用户群体行为的移动社交网络舆情传播动态演化模型研究[J].系统科学与数学，2020，40（12）：2278-2296.
GU Q Y，JU C H，BAO F G.Study on dynamic evolution model of the spread of public opinion in mobile social network incorporatedwith the behavior of user group[J].Journal of Systems Science and Mathematical Sciences，2020，40（12）：2278-2296.
[10] 黄远，刘怡君.多层多属性舆情传播网络的仿真研究[J].系统工程学报，2019，34（6）：844-854.
HUANG Y，LIU Y J.Simulation research on propagation network with multi-layer and multi-attribute public opinions[J].Journal of Systems Engineering，2019，34（6）：844-854.
[11] 陶思怡，梁立波，刘伟，等.网络舆情视域下公众对负面医疗信息的评价分析[J].中国医院，2021，25（2）：55-57.
TAO S Y，LIANG L B，LIU W，et al.Research on public negative medical information cognition from the perspective of online public opinion[J].Chinese Hospitals，2021，25（2）：55-57.
[12] LI J，RAO Y H，JIN F M，et al.Multi-label maximum entropy model for social emotion classificationover short text[J].Neurocomputing，2016，210：247-256.
[13] KAUR S，SIKKA G，AWASTHI L K.Sentiment analysis approach based on N-gram and KNN classifier[C]//Proceedings of the 1st International Conference on Secure Cyber Computing and Communication，Jalandhar，India，2018.
[14] RATHOR A S，AGARWAL A，DIMRI P.Comparative study of machine learning approaches for Amazon reviews[J].Procedia Computer Science，2018，132：1552-1561.
[15] 李文亮，杨秋翔，秦权.多特征混合模型文本情感分析方法[J].计算机工程与应用，2021，57（19）：205-213.
LI W L，YANG Q X，QIN Q.Multi-feature mixed model text sentiment analysis method[J].Computer Engineering and Applications，2021，57（19）：205-213.
[16] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Advances in Neural Information Processing Systems，2017：6000-6010.
[17] 胡任远，刘建华，卜冠南，等.融合BERT的多层次语义协同模型情感分析研究[J].计算机工程与应用，2021，57（13）：176-184.
HU R Y，LIU J H，BU G N，et al.Research on sentiment analysis ofmulti-level semantic collaboration model fused with BERT[J].Computer Engineering and Applications，2021，57（13）：176-184.
[18] 宋云峰，任鸽，杨勇，等.基于注意力的多层次混合融合的多任务多模态情感分析[J].计算机应用研究，2022，39（3）：716-720.
SONG Y F，REN G，YANG Y，et al.Multimodal sentiment analysis based on hybrid feature fusion of multi-level attention mechanism and multi-task learning[J].Application Research of Computers，2022，39（3）：716-720.
[19] DEVLIN J，CHANG M W，LEE K，et al.BERT：pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the North American Chapter of the Association for Computational Linguistics，Minneapolis，USA，2019.
[20] 杨秀璋，武帅，夏换，等.基于主题挖掘和情感分析的“新冠肺炎疫情”舆情分析研究[J].计算机时代，2020（8）：31-36.
YANG X Z，WU S，X H，et al.Public opinion analysis of COVID-19 epidemic using topic mining and emotion analysis[J].Computer Era，2020（8）：31-36.
[21] BLEI D M，NG A Y，JORDAN M I.Latent dirichlet allocation[J].the Journal of Machine Learning Research Archive，2003，3：993-1022.
[22] XING W，MENG F Y，NING J L，et al.Comparative first-principles study of elastic constants of covalent and ionic materials with LDA，GGA，and meta-GGA functionals and the prediction of mechanical hardness[J].Science China（Technological Sciences），2021，64（12）：2755-2761.
[23] 郭业才，张浩然.基于改进LDA和自编码器的调制识别算法[J].系统仿真学报，2021，33（2）：494-500.
GUO Y C，ZHANG H R.Modulation recognition algorithm based on improved LDA and autoencoder[J].Journal of System Simulation，2021，33（2）：494-500.
[24] 张舒，李慧，施珺，等.结合用户评论与评分信息的推荐算法[J].陕西师范大学学报（自然科学版），2020，48（2）：84-91.
ZHANG S，LI H，SHI J，et al.Research on recommendation algorithm combining user comments and rating information[J].Journal of Shaanxi Normal University（Natural Science Edition），2020，48（2）：84-91.
[25] PAPPAS S S，EKONOMOU L，KARAMPELAS P，et al.Electricity demand load forecasting of the Hellenic power system using an ARMA model[J].Electric Power Systems Research，2010，80（3）：256-264.
[26] 张利.基于时间序列ARIMA模型的分析预测算法研究及系统实现[D].镇江：江苏大学，2008.
ZHANG L.Study of the time series forecasting algorithm and system realization based on the ARIMA model[D].Zhenjiang：Jiangsu University，2008.
[27] 罗伟.基于合作对策的股指时间序列组合预测[J].系统仿真学报，2018，30（6）：2086-2094.
LUO W.Combination forecasting of stock index time series based on cooperative game theory[J].Journal of System Simulation，2018，30（6）：2086-2094.
[28] 叶雪梅，毛雪岷，夏锦春，等.文本分类TF-IDF算法的改进研究[J].计算机工程与应用，2019，55（2）：104-109.
YE X M，MAO X M，XIA J C，et al.Improved approach to TF-IDF algorithm in text classification[J].Computer Engineering and Applications，2019，55（2）：104-109.