Deep Learning and Network Analysis: Classifying and Visualizing Geologic Hazard Reports

Abstract

If progress is to be made toward improving geohazard management and emergency decision-making, then lessons need to be learned from past geohazard information. A geologic hazard report provides a useful and reliable source of information about the occurrence of an event, along with detailed information about the condition or factors of the geohazard. Analyzing such reports, however, can be a challenging process because these texts are often presented in unstructured long text formats, and contain rich specialized and detailed information. Automatically text classification is commonly used to mine disaster text data in open domains (e.g., news and microblogs). But it has limitations to performing contextual long-distance dependencies and is insensitive to discourse order. These deficiencies are most obviously exposed in long text fields. Therefore, this paper uses the bidirectional encoder representations from Transformers (BERT), to model long text. Then, utilizing a softmax layer to automatically extract text features and classify geohazards without manual features. The latent Dirichlet allocation (LDA) model is used to examine the interdependencies that exist between causal variables to visualize geohazards. The proposed method is useful in enabling the machine-assisted interpretation of text-based geohazards. Moreover, it can help users visualize causes, processes, and other geohazards and assist decision-makers in emergency responses.

Keywords

geologic hazard / network analysis / latent dirichlet allocation / text classification / deep learning

References

[] Adhikari A, Ram A, Tang R, et al.. . DocBERT: BERT for Document Classification, 2019 arXiv: 1904.08398

[] Behera B, Kumaravelan G. Text Document Classification Using Fuzzy Rough Set Based on Robust Nearest Neighbor (FRS-RNN). Soft Computing, 2021, 25(15): 9915-9923

[] Blei D M, Ng A Y, Jordan M I. Latent Dirichlet Allocation. Journal of Machine Learning Research, 2003, 3: 993-1022

[] Bojanowski P, Grave E, Joulin A, et al.. Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics, 2017, 5: 135-146

[] Brooks B. Shifting the Focus of Strategic Occupational Injury Prevention. Safety Science, 2008, 46(1): 1-21

[] Calafiore A, Palmer G, Comber S, et al.. A Geographic Data Science Framework for the Functional and Contextual Analysis of Human Dynamics within Global Cities. Computers, Environment and Urban Systems, 2021, 85: 101539

[] Chen J A, Yang Z C, Yang D Y. . MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification, 2020 arXiv: 2004.12239

[] Chen J N, Huang H K, Tian S F, et al.. Feature Selection for Text Classification with Naïve Bayes. Expert Systems with Applications, 2009, 36(3): 5432-5435

[] Church K W. Word2Vec. Natural Language Engineering, 2017, 23(1): 155-162

[] Croitoru A, Wayant N, Crooks A, et al.. Linking Cyber and Physical Spaces through Community Detection and Clustering in Social Media Feeds. Computers, Environment and Urban Systems, 2015, 53: 47-64

[] Devlin J, Chang M W, Lee K, et al.. . BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding, 2018 arXiv: 1810.04805

[] Goodchild M F. Citizens as Sensors: The World of Volunteered Geography. GeoJournal, 2007, 69(4): 211-221

[] Granell C, Ostermann F O. Beyond Data Collection: Objectives and Methods of Research Using VGI and Geo-Social Media for Disaster Management. Computers, Environment and Urban Systems, 2016, 59: 231-243

[] Guo B, Zhang C X, Liu J M, et al.. Improving Text Classification with Weighted Word Embeddings via a Multi-Channel TextCNN Model. Neurocomputing, 2019, 363(C): 366-374

[] Haworth B. Emergency Management Perspectives on Volunteered Geographic Information: Opportunities, Challenges and Change. Computers, Environment and Urban Systems, 2016, 57: 189-198

[] Herfort B, de Albuquerque J P, Schelhorn S J, et al.. Huerta J, Schade S, Granell C, et al.. Exploring the Geographical Relations between Social Media and Flood Phenomena to Improve Situational Awareness. Connecting a Digital Europe Through Location and Place, 2014 Cham Springer 55-71

[] Hong F, Lai C F, Guo H Q, et al.. FLDA: Latent Dirichlet Allocation Based Unsteady Flow Analysis. IEEE Transactions on Visualization and Computer Graphics, 2014, 20(12): 2545-2554

[] Huang Q Y, Cervone G, Zhang G M. A Cloud-Enabled Automatic Disaster Analysis System of Multi-Sourced Data Streams: An Example Synthesizing Social Media, Remote Sensing and Wikipedia Data. Computers, Environment and Urban Systems, 2017, 66: 23-37

[] Huang X, Li Z L, Wang C Z, et al.. Identifying Disaster Related Social Media for Rapid Response: A Visual-Textual Fused CNN Architecture. International Journal of Digital Earth, 2020, 13(9): 1017-1039

[] Jelodar H, Wang Y L, Yuan C, et al.. Latent Dirichlet Allocation (LDA) and Topic Modeling: Models, Applications, a Survey. Multimedia Tools and Applications, 2019, 78(11): 15169-15211

[] Joulin A, Grave E, Bojanowski P, et al.. . Bag of Tricks for Efficient Text Classification, 2016 arXiv: 1607.01759

[] Kaity M, Balakrishnan V. Sentiment Lexicons and Non-English Languages: A Survey. Knowledge and Information Systems, 2020, 62(12): 4445-4480

[] . In Proceedings of the AAAI Conference On Artificial Intelligence, 2017, 31(1)

[] Ma K, Tian M, Tan Y J, et al.. Ontology-Based BERT Model for Automated Information Extraction from Geological Hazard Reports. Journal of Earth Science, 2023, 34(5): 1390-1405

[] Mikolov T, Sutskever I, Chen K, et al.. . Distributed Representations of Words and Phrases and Their Compositionality, 2013 arXiv: 1310.4546

[] Ogie R I, Clarke R J, Forehead H, et al.. Crowdsourced Social Media Data for Disaster Management: Lessons from the PetaJakarta. org Project. Computers, Environment and Urban Systems, 2019, 73: 108-117

[] Pennington J, Socher R, Manning C D. Glove: Global Vectors for Word Representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), October 25–29, 2014, Doha, Qatar, 2014 Stroudsburg, PA, USA Association for Computational Linguistics

[] Peters M E, Neumann M, Iyyer M, et al.. . Deep Contextualized Word Representations, 2018 arXiv: 1802.05365

[] Poonkuzhali G, Thiagarajan K, Sarukesi K, et al.. Signed Approach for Mining Web Content Outliers. International Journal of Computer and Information Engineering, 2009, 3(8): 2124-2128

[] Qiu Q J, Xie Z, Zhang D, et al.. Knowledge Graph for Identifying Geological Disasters by Integrating Computer Vision with Ontology. Journal of Earth Science, 2023, 34(5): 1418-1432

[] Resch B, Uslánder F, Havas C. Combining Machine-Learning Topic Models and Spatiotemporal Analysis of Social Media Data for Disaster Footprint and Damage Assessment. Cartography and Geographic Information Science, 2018, 45(4): 362-376

[] Ruhnau B. Eigenvector-Centrality—A Node-Centrality?. Social Networks, 2000, 22(4): 357-365

[] Sun X, Ma X H, Ni Z W, et al.. A New LSTM Network Model Combining TextCNN. International Conference on Neural Information Processing, 2018 Cham Springer 416-424

[] Suto J, Oniga S. Efficiency Investigation from Shallow to Deep Neural Network Techniques in Human Activity Recognition. Cognitive Systems Research, 2019, 54: 37-49

[] Tang R, Lu Y, Liu L, et al.. . Distilling Task-Specific Knowledge from BERT into Simple Neural Networks, 2019 arXiv: 1903.12136

[] Trstenjak B, Mikac S, Donko D. KNN with TF-IDF Based Framework for Text Categorization. Procedia Engineering, 2014, 69: 1356-1364

[] Wang Y D, Ruan S S, Wang T, et al.. Rapid Estimation of an Earthquake Impact Area Using a Spatial Logistic Growth Model Based on Social Media Data. International Journal of Digital Earth, 2019, 12(11): 1265-1284

[] Wang Z L, Lai C G, Chen X H, et al.. Flood Hazard Risk Assessment Model Based on Random Forest. Journal of Hydrology, 2015, 527: 1130-1141

[] Yao F, Wang Y. Domain-Specific Sentiment Analysis for Tweets during Hurricanes (DSSA-H): A Domain-Adversarial Neural-Network-Based Approach. Computers, Environment and Urban Systems, 2020, 83: 101522

[] Zhang W, Yoshida T, Tang X J. Text Classification Based on Multi-Word with Support Vector Machine. Knowledge-Based Systems, 2008, 21(8): 879-886

[] Zhang Y J, Chen Q Y, Yang Z H, et al.. BioWordVec, Improving Biomedical Word Embeddings with Subword Information and MeSH. Scientific Data, 2019, 6: 52

[] Zhong B T, Pan X, Love P E D, et al.. Deep Learning and Network Analysis: Classifying and Visualizing Accident Narratives in Construction. Automation in Construction, 2020, 113: 103089

[] Zhou Y, Chen C, Zhang P, et al.. Structured Data Extraction Method of Hazard Description Text Based on Strong Part-of-Speech Matching. Journal of Physics: Conference Series, 2021, 1746(1): 012056

[] Zhu Y H, Wen Z Q, Wang P, et al.. A Method of Building Chinese Basic Semantic Lexicon Based on Word Similarity. 2009 Chinese Conference on Pattern Recognition, 2009 Nanjing, China IEEE