Abstract Online public opinion usually spreads rapidly and widely, thus a small incident probably evolves into a large social crisis in a very short time, and results in a heavy loss in credit or economic aspects. We propose a method to rate the crisis of online public opinion based on a multi-level index system to evaluate the impact of events objectively. Firstly, the dissemination mechanism of online public opinion is explained from the perspective of information ecology. According to the mechanism, some evaluation indexes are selected through correlation analysis and principal component analysis. Then, a classification model of text emotion is created via the training by deep learning to achieve the accurate quantification of the emotional indexes in the index system. Finally, based on the multi-level evaluation index system and grey correlation analysis, we propose a method to rate the crisis of online public opinion. The experiment with the real-time incident show that this method can objectively evaluate the emotional tendency of Internet users and rate the crisis in different dissemination stages of online public opinion. It is helpful to realizing the crisis warning of online public opinion and timely blocking the further spread of the crisis.

References

[1] Abed A., Jingling Y., and Li L., “Research-based- named Entity Recognition Learning Text Biomedical Extraction by Adoption of Training Bidirectional Language Model (BiLM),” Journal of Computers, vol. 31, no. 4, pp.157-173, 2020.

[2] Amina B. and Azim T., “SCANCPECLENS: A Framework for Automatic Lexicon Generation and Sentiment Analysis of Micro Blogging Data 1 2 3 4 2019/4/11 18:002019/4/12 0:002019/4/12 6:002019/4/12 12:002019/4/12 18:002019/4/13 0:002019/4/13 6:002019/4/13 12:002019/4/13 18:002019/4/14 0:002019/4/14 6:002019/4/14 12:002019/4/14 18:002019/4/15 0:00 three indicators seven indicators eleven indicators fourteen indicators eighteen indicators Rating the Crisis of Online Public Opinion Using a Multi-Level Index System 607 on China Pakistan Economic Corridor,” IEEE Access, vol. 7, pp. 133876-133887, 2019.

[3] Bai Q, Xu Z, Liu Y, Miao X., and Xiu Q., “The Web Crawler Based on Python to Obtain Public Emotional Data Analysis-Take The Weibo Hot Rearch Data as An Example,” in Proceedings of 7th International Conference on Systems and Informatics, Chongqing, pp. 1-6, 2021.

[4] Cao H., Wang J., and Wang Z., “Opinion Leaders Discovery in Social Networking Site Based on the Theory of Propagation Probability,” in Proceedings of 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, Xi'an, pp. 700- 704, 2018.

[5] Chen X., Duan S., and Wang L., “Research on Trend Prediction and Evaluation of Network Public Opinion,” Concurrency and Computation: Practice and Experience, vol. 29, vol. 4, pp. e4212, 2017.

[6] Dai Y. and Fei Y., “Research on Information Mining and Evaluation Index System Based on Internet Public Opinion Security,” Information Studies: Theory and Application, vol. 31, pp. 873- 876, 2008.

[7] Huang H., “Research on the Construction of Evaluation Index System Formed in the Decline Period of Multimedia Network Public Opinion,” Information Theory and Practice, vol. 43, pp. 76- 81, 2020.

[8] Kim H. and Laskowski M., Moghadas S., Sajad A., and Asif M., “A Framework for Comparing Early Warning Systems Across Domains: A Step Toward A Data-Integrated Public Health EWS,” in Proceedings of the IEEE 15th International Conference on Information Reuse and Integration, Redwood City, 2015.

[9] Lan Y., “On Construction of Emergency Network Safety Evaluation Index System,” Journal of Intelligence, vol. 30, pp. 73-76, 2008.

[10] Li Y. and Li J., “Quantitative Evaluation Index System and Quantitative Calculation Method for the Influence Degree of Network Public Opinion,” Information Network Security, vol. 9, pp. 196-200, 2015.

[11] Lian Y., Dong X., and Liu Y., “Topological Evolution of the Internet Public Opinion,” in Proceedings of the Physica A: Statistical Mechanics and its Applications, vol. 486, pp. 567- 578, 2015.

[12] Luo G., Zhang Z., Bao Z., and Chen N., “A Novel Method for the Time Series Data Processing and Analysis of Social Networks,” Journal of Computers, vol. 31, no. 4, pp. 273-287, 2020.

[13] Ma N. and Liu Y., “SuperedgeRank Algorithm and its Application in Identifying Opinion Leader of Online Public Opinion Supernetwork,” Expert Systems with Applications, vol. 41, vol. 4, pp. 1357-1368, 2014.

[14] Mao X., Chang S., Shi J., Li F., and Shi R., “Sentiment-Aware Word Embedding for Emotion Classification,” Applied Sciences, vol. 9, no. 7, pp. 1334, 2019.

[15] Meng F., Zheng Y., Bao S., Wang J., and Yang S., “Formulaic Language Identification Model Based on GCN Fusing Associated Information,” PeerJ Computer Science, vol. 8, pp. e984, 2022.

[16] Naveau A., Smirani R., and Catros S., Oliveira H., Fricain J., Devillard R., “A Bibliometric Study to Assess Bioprinting Evolution,” Applied Sciences, vol. 7, no. 12, pp. 1331, 2017.

[17] Sun X., Wang H., and Li W., “Fast Online Training with Frequency-Adaptive Learning Rates for Chinese Word Segmentation and New Word Detection,” in Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, Jeju Island, pp. 253- 262, 2012.

[18] Tiwari D. and Nagpal B., “Enhanced Long Short- Term Memory (ELSTM) Model for Sentiment Analysis,” The International Arab Journal of Information Technology, vol. 18, no. 6, pp. 846- 855, 2021.

[19] Wang L. and Chen L., “A Summary of Theoretical Research on Internet Public Opinion Evolution, Early Warning and Coping at Home and Abroad,” Library Journal, vol. 37, pp. 4-13, 2018.

[20] Wu Y., Song Y., Wang F., Zhou Y., and Li M., “Online Public Opinion Guidance Strategy for College Students in the Era of We Media,” Journal of Computer and Communications, vol. 7, pp. 79-87, 2019.

[21] Xing Y., “Research on Negative Network Public Opinion Monitoring Index System Based on Information Entropy,” Journal of Modern Information, vol. 38, pp.41-47, 2018.

[22] Xue B., Fu C., and Zhang S., “A Study on Sentiment Computing and Classification of Sina Weibo with Word2vec,” in Proceedings of IEEE International Congress on Big Data, Anchorage, 2014.

[23] Yan S., Su Q., Gong Z., and Zeng X., “Fractional Order Time-Delay Multivariable Discrete Grey Model for Short-Term Online Public Opinion Prediction,” Expert Systems with Applications, vol. 197, pp. 116691, 2022.

[24] Yin F., Zhang B., Su G., and Zhang R., “Research On The Public Opinion Pre-Warning Based on The Logistic Model,” in Proceedings of 8th IEEE International Conference on Software Engineering and Service Science, Beijing, pp. 381-385, 2017.

[25] Zhang Y. and Chen Z., “SETQR Propagation Model for Social Networks,” IEEE Access, vol. 7, pp.12753-12754, 2019. 608 The International Arab Journal of Information Technology, Vol. 19, No. 4, July 2022

[26] Zhang Y., “Network Opinion Risk Evaluation Index System Based on the Cycle of Emergency,” Information Science, vol. 30, pp.1034-1037, 2012.

[27] Zhao L., “Research on Public Opinion Index System of Chinese Microblog,” in Proceedings of the IEEE International Conference on Software Engineering and Service Science, pp. 385-388, 2014. Fanqi Meng is an associate professor at NEEPU. He was born in Tongliao, Inner Mongolia, China in 1981. He received his Ph.D. degree in computer application technology from Harbin Institute of Technology, Harbin, in 2018. His research interests include software safety, natural language processing, fault diagnosis of electric power equipment and other aspects, involve software engineering, artificial intelligence, data mining and other fields. Xixi Xiao was born in Shangqu, Henan, China in 1995. She received the M.E. degree from Northeast Electric Power University. Her research interest include online public opinion and artificial intelligence. Jingdong Wang is an associate professor at NEEPU. He was born in Changchun, Jilin, China in 1980. He received the Ph.D. degree in information science from University of Science and technology of China, in 2017. His research interests include public security, natural language processing, knowledge graph and other aspects.