Data Mining and Spatial Analysis of Social Media Text Based on the BERT-CNN Model to Achieve Situational Awareness: a Case Study of COVID-19

doi:10.11947/j.JGGS.2022.0205

Abstract

Abstract:

In response to the COVID-19, social media big data has played an important role in epidemic warning, tracking the source of infection, and public opinion monitoring, providing strong technical support for China’s epidemic prevention and control work. The paper used Sina Weibo posts related to COVID-19 hashtags as the data source, and built a BERT-CNN deep learning model to perform fine-grained and high-precision topic classificationon massive social media posts. Taking Shenzhen as a region of interest, we mined the “epidemic data bulletin” and “daily life impact” posts during the epidemic for spatial analysis. The results show that the confirmed communities and designated hospitals in Shenzhen as a whole present the characteristics of “sparse east and dense west”, and there is a strong positive spatial correlation between the number of confirmed cases and social media response. Specifically, Nanshan District, Futian District and Luohu District have more confirmed cases due to large population movements and dense transportation networks, and social media has responded more violently, and people’s lives have been greatly affected. However, Yantian District, Pingshan District and Dapeng New District showed opposite characteristics. The case study results further show that using deep learning methods to mine text information in social media is scientifically feasible for improving situational awareness and decision support during the COVID-19.

Key words: COVID-19; Sina Weibo; BERT-CNN; topic classification; situational awareness

Jiawei ZHANG,Hua QI. Data Mining and Spatial Analysis of Social Media Text Based on the BERT-CNN Model to Achieve Situational Awareness: a Case Study of COVID-19[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(2): 38-48.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

References 26

[1]	ZHAO Yuxin, CHENG Sixiang, YU Xiaoyan, et al. Chinese public’s attention to the COVID-19 epidemic on social media: observational descriptive study[J]. Journal of Medical Internet Research, 2020, 22(5): e18825. doi: 10.2196/18825
[2]	YU Meng, LI Zhiyong, YU Zhicheng, et al. Communication related health crisis on social media: a case of COVID-19 outbreak[J]. Current Issues in Tourism, 2021, 24(19): 2699-2705. doi: 10.1080/13683500.2020.1752632
[3]	WANG Zheye, YE Xinyue. Social media analytics for natural disaster management[J]. International Journal of Geographical Information Science, 2018, 32(1): 49-72. doi: 10.1080/13658816.2017.1367003
[4]	GUTIERREZ B J, ZENG Jucheng, ZHANG Dongdong, et al. Document classification for COVID-19 literature[C]//Proceedings of Findings of the Association for Computational Linguistics: EMNLP 2020. [S.l.]:Association for Computational Linguistics, 2020.
[5]	ZHOU Chenghu, SU Fenzhen, PEI Tao, et al. COVID-19: challenges to GIS with big data[J]. Geography and Sustainability, 2020, 1(1): 77-87. doi: 10.1016/j.geosus.2020.03.005
[6]	HAN Xuehua, WANG Juanle, ZHANG Min, et al. Using social media to mine and analyze public opinion related to COVID-19 in China[J]. International Journal of Environmental Research and Public Health, 2020, 17(8): 2788. doi: 10.3390/ijerph17082788
[7]	NEMES L, KISS A. Social media sentiment analysis based on COVID-19[J]. Journal of Information and Telecommunication, 2021, 5(1): 1-15. doi: 10.1080/24751839.2020.1790793
[8]	WANG Tianyi, LU Ke, CHOW K P, et al. COVID-19 sensing: negative sentiment analysis on social media in China via BERT model[J]. IEEE Access, 2020, 8: 138162-138169. doi: 10.1109/ACCESS.2020.3012595
[9]	YANG Chaowei, SHA Dexuan, LIU Qian, et al. Taking the pulse of COVID-19: a spatiotemporal perspective[J]. International Journal of Digital Earth, 2020, 13(10): 1186-1211. doi: 10.1080/17538947.2020.1809723
[10]	TIAN Huaiyu, LIU Yonghong, LI Yidan, et al. An investigation of transmission control measures during the first 50 days of the COVID-19 epidemic in China[J]. Science, 2020, 368(6491): 638-642. doi: 10.1126/science.abb6105 pmid: 32234804
[11]	CUI Hao, KERTÉSZ J. Attention dynamics on the Chinese social media Sina Weibo during the COVID-19 pandemic[J]. EPJ Data Science, 2021, 10(1): 8. doi: 10.1140/epjds/s13688-021-00263-0 pmid: 33552838
[12]	HU Yong, HUANG Heyan, CHEN Anfan, et al. Weibo-COV: a large-scale COVID-19 social media dataset from Weibo[C]//Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020. [S.l.]:Association for Computational Linguistics, 2020.
[13]	MUHAMMAD R, ZHAO Yaolong, LIU Fan. Spatiotemporal analysis to observe gender based check-in behavior by using social media big data: a case study of Guangzhou, China[J]. Sustainability, 2019, 11(10): 2822. doi: 10.3390/su11102822
[14]	LIU Kui, LI Li, JIANG Tao, et al. Chinese public attention to the outbreak of Ebola in West Africa: evidence from the online big data platform[J]. International Journal of Environmental Research and Public Health, 2016, 13(8): 780. doi: 10.3390/ijerph13080780
[15]	FUNG I C H, FU K W, YING Yuchen, et al. Chinese social media reaction to the MERS-CoV and avian influenza A (H7N9) outbreaks[J]. Infectious Diseases of Poverty, 2013, 2(1): 31. doi: 10.1186/2049-9957-2-31
[16]	DEVLIN J, CHANG Mingwei, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Minneapolis, MN: Association for Computational Linguistics, 2019.
[17]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, CA: Curran Associates Inc, 2017.
[18]	ZHANG Yunxiang, RAO Zhuyi. Deep neural networks with pre-train model BERT for aspect-level sentiments classification[C]//Proceedings of the IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC). Chongqing, China: IEEE, 2020: 923-927.
[19]	GAO Zhengjie, FENG Ao, SONG Xinyu, et al. Target-dependent sentiment classification with BERT[J]. IEEE Access, 2019, 7: 154290-154299. doi: 10.1109/ACCESS.2019.2946594
[20]	WANG Ziniu, HUANG Zhilin, GAO Jianling. Chinese text classification method based on BERT word embedding[C]//Proceedings of the 5th International Conference on Mathematics and Artificial Intelligence. Chengdu, China: ACM, 2020: 66-71.
[21]	KIM Y. Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha, Qatar: Association for Computational Linguistics, 2014.
[22]	LI Lifang, ZHANG Qingpeng, WANG Xiao, et al. Characterizing the propagation of situational information in social media during COVID-19 epidemic: a case study on Weibo[J]. IEEE Transactions on Computational Social Systems, 2020, 7(2): 556-562. doi: 10.1109/TCSS.2020.2980007
[23]	AI Tinghua, LEI Yingzhe, XIE Peng, et al. Quantifying spatial accessibility of Shenzhen’s hospitals by the Isochrone model[J]. Journal of Geo-information Science, 2020, 22(1): 113-121.
[24]	YENISETTY P T, BAHADURE P. Spatial accessibility measures to educational facilities from public transit: a case of Indian cities[J]. Smart and Sustainable Built Environment, 2021, 10(2): 258-273. doi: 10.1108/SASBE-11-2019-0153
[25]	YANG Tengfei, XIE Jibo, LI Guoqing, et al. Social media big data mining and spatio-temporal analysis on public emotions for disaster mitigation[J]. ISPRS International Journal of Geo-Information, 2019, 8(1): 29. doi: 10.3390/ijgi8010029
[26]	DE ALBUQUERQUE J P, HERFORT B, BRENNING A, et al. A geographic approach for combining social media and authoritative data towards identifying useful information for disaster management[J]. International Journal of Geographical Information Science, 2015, 29(4): 667-689. doi: 10.1080/13658816.2014.996567

Category	precision	recall	f1_score
Epidemic data bulletin	0.996	0.992	0.994
Blessing/positive energy prayer	0.9685	0.983	0.9757
Epidemic prevention measures	0.9657	0.986	0.9758
Help and consultation	0.998	0.999	0.9985
Typical character/moving events	0.9878	0.974	0.9809
Government and social assistance	0.9929	0.983	0.9879
Resumption of work and production	0.9861	0.991	0.9885
Daily life impact	0.9594	0.97	0.9647
Medical science/research progress	0.9841	0.989	0.9865
Others	0.9722	0.943	0.9574
Overall	0.981	0.981	0.9809