Knowledge map of online public opinions for emergencies

doi:10.23919/JSEE.2024.000054

Abstract

Abstract:

With the popularization of social media, public opinion information on emergencies spreads rapidly on the Internet, the impact of negative public opinions on an event has become more significant. Based on the organizational form of public opinion information, the knowledge graph is used to construct the knowledge base of public opinion risk cases on the emergency network. The emotion recognition model of negative public opinion information based on the bi-directional long short-term memory (BiLSTM) network is studied in the model layer design, and a linear discriminant analysis (LDA) topic extraction method combined with association rules is proposed to extract and mine the semantics of negative public opinion topics to realize further in-depth analysis of information topics. Focusing on public health emergencies, knowledge acquisition and knowledge processing of public opinion information are conducted, and the experimental results show that the knowledge graph framework based on the construction can facilitate in-depth theme evolution analysis of public opinion events, thus demonstrating important research significance for reducing online public opinion risks.

Key words: knowledge graph, sentiment classification, topic extraction, association rule

Shuang GUAN, Zihan FANG, Changfeng WANG. Knowledge map of online public opinions for emergencies[J]. Journal of Systems Engineering and Electronics, 2025, 36(2): 436-445.

Figures/Tables 12

Fig 1

Table 1

Fig 2

Fig 3

Table 2

Table 3

Table 4

Table 5

Fig 4

Table 6

Fig 5

Table 7

References 40

1	ZHANG G Z Constructing the autonomous knowledge system of national security studies under the guidance of the overall national security concept. Ideological Frontline, 2023, 49 (3): 1- 7.
2	KELLY D, KOAY A, MINEVA G, et al A scoping review of non-professional medication practices and medication safety outcomes during public health emergencies. Public Health, 2023, 214, 50- 60. doi: 10.1016/j.puhe.2022.10.026
3	ZHANG L, ZHAO W J, SUN B B, et al How scientific research reacts to international public health emergencies: a global analysis of response patterns. Scientometrics, 2020, 124 (1): 747- 773. doi: 10.1007/s11192-020-03531-4
4	SONG P P, KARAKO T COVID-19: real-time dissemination of scientific information to fight a public health emergency of international concern. Bioscience Trends, 2020, 14 (1): 1- 2. doi: 10.5582/bst.2020.01056
5	CHEN X G, DUAN S, WANG L D Research on clustering analysis of Internet public opinion. Cluster Computing, 2019, 22, 5997- 6007. doi: 10.1007/s10586-018-1781-3
6	ZHOU Q Q, JING M Multidimensional mining of public opinion in emergency events. The Electronic Library, 2020, 38 (3): 545- 560. doi: 10.1108/EL-12-2019-0276
7	ZHAO J H, ZENG D L, QIN J T, et al Simulation and modeling of microblog-based spread of public opinions on emergencies. Neural Computing and Applications, 2021, 33, 547- 564. doi: 10.1007/s00521-020-04919-2
8	HUANG W D, WANG Q, CAO J Tracing public opinion propagation and emotional evolution based on public emergencies in social networks. International Journal of Computers Communications & Control, 2018, 13 (1): 129- 142.
9	QIU Z G, YUAN X A, YIN Y C. Research on social governance of network public opinion: an evolutionary game model. Discrete Dynamics in Nature and Society, 2023, 2023: 8530530.
10	CHEN M, ZHANG L L Application of edge computing combined with deep learning model in the dynamic evolution of network public opinion in emergencies. The Journal of Supercomputing, 2023, 79 (2): 1526- 1543. doi: 10.1007/s11227-022-04733-8
11	GAO G, WANG T Y, ZHENG X R, et al A systems dynamics simulation study of network public opinion evolution mechanism. Journal of Global Information Management, 2019, 27 (4): 189- 207. doi: 10.4018/JGIM.2019100110
12	LIU L Y, TU Y, ZHOU X Y How local outbreak of COVID-19 affect the risk of internet public opinion: a Chinese social media case study. Technology in Society, 2022, 71, 102113. doi: 10.1016/j.techsoc.2022.102113
13	QI Z M, CHEN J B Information-centric networking based content collection and caching mechanism for network public opinion. Internet Technology Letters, 2023, 6 (2): e369. doi: 10.1002/itl2.369
14	ZHAO Z F Intelligent analysis and positioning of political public opinion in universities. International Journal on Artificial Intelligence Tools, 2022, 31 (4): 2240013. doi: 10.1142/S0218213022400139
15	ZHONG Q H, DING L, LIU J H, et al. Knowledge graph augmented network towards multiview representation learning for aspect-based sentiment analysis. IEEE Trans. on Knowledge and Data Engineering, 2023. DOI:10.1109/TKDE.2023.3250499.
16	NIE W Z, BAO Y R, ZHAO Y, et al. Long dialogue emotion detection based on commonsense knowledge graph guidance. IEEE Trans. on Multimedia, 2023. DOI: 10.1109/TMM.2023.3267295.
17	ZHOU Y Q, JIANG Y J Research on the discovery of hot topics in university network public opinion based on knowledge graph. Forum on Industry and Technology, 2023, 22 (19): 47- 49.
18	SIKOS, LESLIE F Cybersecurity knowledge graphs. Knowledge and Information Systems, 2023, 65 (9): 3511- 3531. doi: 10.1007/s10115-023-01860-3
19	WANG G H, CHI Y X, LIU Y J, et al Studies on a multidimensional public opinion network model and its topic detection algorithm. Information Processing & Management, 2019, 56 (3): 584- 608.
20	HUANG L C, HOU Z M, FANG Y L, et al Evolution of CCUS technologies using LDA topic model and derwent patent data. Energies, 2023, 16 (6): 2556. doi: 10.3390/en16062556
21	BHAT M R, KUNDROO M A, TARRAY T A, et al Deep LDA: a new way to topic model. Journal of Information and Optimization Sciences, 2020, 41 (3): 823- 834. doi: 10.1080/02522667.2019.1616911
22	LI X M, XU J J. Machine learning based on association rules about automatic course data mining. Proc. of the 5th International Conference on Advanced Electronic Materials, Computers and Software Engineering , 2022: 719−722.
23	ZHANG M L, QIN S M, ZHU X X Information diffusion under public crisis in BA scale-free network based on SEIR model—Taking COVID-19 as an example. Physica A: Statistical Mechanics and its Applications, 2021, 571, 125848. doi: 10.1016/j.physa.2021.125848
24	BAALBAKI J, ZIZKA L Egyptian crises and destination brand image: the resurrection of the mummy. Current Issues in Tourism, 2024, 27 (6): 887- 905. doi: 10.1080/13683500.2023.2187280
25	COMFORT L K, KAPUCU N, KO K, et al Crisis decision-making on a global scale: transition from cognition to collective action under threat of COVID-19. Public Administration Review, 2020, 80 (4): 616- 622. doi: 10.1111/puar.13252
26	LIU W B, WANG Z D, LIU X H, et al A survey of deep neural network architectures and their applications. Neurocomputing, 2017, 234, 11- 26. doi: 10.1016/j.neucom.2016.12.038
27	SHERSTINSKY A Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 2020, 404, 132306. doi: 10.1016/j.physd.2019.132306
28	RODRIGUEZ P L, SPIRLING A Word embeddings: what works, what doesn’t, and how to tell the difference for applied research. The Journal of Politics, 2022, 84 (1): 101- 115. doi: 10.1086/715162
29	HUANG J J, LI P W, PENG M, et al Research on topic model based on deep learning. Chinese Journal of Computers, 2020, 43 (5): 827- 855.
30	UTHIRAPATHY S E, SANDANAM D Topic modelling and opinion analysis on climate change twitter data using LDA and BERT model. Procedia Computer Science, 2023, 218, 908- 917. doi: 10.1016/j.procs.2023.01.071
31	SAI T K V, LOHITH K, SAI M P, et al. Text analysis on twitter data using LSA and LDA. Proc. of the International Conference on Computer Communication and Informatics, 2023. DOI: 10.1109/ICCCI56745.2023.10128417.
32	AL-KEBSI F M, AL-WAGIB K S, AL-MAQALEH B M. An effective algorithm for mining interesting maximal association rules. Proc. of the International Conference of Modern Trends in Information and Communication Technology Industry, 2021. DOI: 10.1109/MTICTI53925.2021.9664770.
33	HE B, XIAO W, HU Y Y, et al. A novel muilti-layer associate rules mining algorithm for relations between carbon emission futures price and european economy. Proc. of the 6th International Conference on E-Business and Internet, 2022: 313−318.
34	LI X, CHEN C, YANG F Q Exploring hazardous chemical explosion accidents with association rules and Bayesian networks. Reliability Engineering & System Safety, 2023, 233, 109099.
35	LIANG K J, LIANG Q, YANG B R. Causal association rule mining methods based on fuzzy state description. Journal of Systems Engineering and Electronics, 2006, 17(1): 193−199.
36	SAEED M M, AGHBARI Z Artc: feature selection using association rules for text classification. Neural Computing and Applications, 2022, 34 (24): 22519- 22529. doi: 10.1007/s00521-022-07669-5
37	LIU P C, HUANG Y L, WANG P, et al. Construction of typhoon disaster knowledge graph based on graph database Neo4j. Proc. of the Chinese Control and Decision Conference, 2020: 3612−3616.
38	STOTHERS J A M, NGUYEN A. Can Neo4j replace PostgreSQL in healthcare? AMIA Summits on Translational Science Proceedings, 2020, 2020: 646−653.
39	KIM D H, IM H S, HYEON J H, et al Development of the rule-based smart tourism chatbot using Neo4J graph database. International Journal of Internet, Broadcasting and Communication, 2021, 13 (2): 179- 186.
40	SAAD M, ZHANG Y Z, TIAN J H, et al A graph database for life cycle inventory using Neo4j. Journal of Cleaner Production, 2023, 393, 136344. doi: 10.1016/j.jclepro.2023.136344

Entity	Definition	Relationship	Interpretation
Event	Public opinion events that arouse wide concern	EventEmotion	It expresses proportion of negative emotion in the event
Affective proportion	Proportion of netizens expressing negative emotions	EventTopic	It refers to the negative topic in the event
Time	Time when public opinion events occur	EventTime	It corresponds to the initial occurrence time of the event
Message	Place, person, etc., described by the event	EventKeyword	It constitutes key elements of the event information
Subject term	Themes drawn from negative public opinion events	Associate	It indicates relationship between negative subject words

Topic comment	Participle and de-stop word
“Please trust our medical staff, and we will get through this together!!”	“Please, believe, medical staff, together, and get through this”
“Difficulty breathing when the spray runs out... Do you have to buy it yourself???”	“Spray, breathe, difficulty, use up, can’t, yourself, and buy”
“//@There is no Mr. Sheep: who is the rumor of double coptis.”	“Double coptis, rumors, count, and who’s”

Model	Precision	Recall	F1
BiLSTM	89.8	88.4	89.1

Public opinion event	Negative text count	Number of non-negative texts	Total number of public opinion texts	Proportion of negative emotion/%
Infectious disease experts say there is no time to lose	1920	462	2382	80.60
The number of cases in Wuhan continues to rise	4362	1568	5930	73.56
Hubei Red Cross Society’s dereliction of duty	3047	531	3578	85.16
Li Wenliang’s wife’s statement	830	458	1288	64.44
Remarkable progress has been made in the prevention and control of COVID-19	690	867	1557	44.31

Serial number	Subject term	Subject word strong association rule
1	Strict investigation, spread, control, dereliction of duty, and infection	Control ==> spread, dereliction of duty ==> strict investigation, and infection ==> control
2	Isolation, shortages, hospitals, donations, and panic	Hospital ==> shortage, quarantine ==> panic, and shortage ==> donation
3	Immunity, incubation period, risk, disinfection, and severe	Immunization => risk, incubation period => severe, and risk ==> disinfection
4	Nucleic acids, weathering difficulties, vaccines, confidence, and inflection points	Inflection point ==> confidence, nucleic acid ==> vaccine, and confidence ==> tide over the difficulties