Automated Seeded Latent Dirichlet Allocation for Social Media Based Event Detection and Mapping

C. Ferner; C. Havas; E. Birnbacher; S. Wegenkittl; B. Resch

doi:10.3390/INFO11080376

Automated Seeded Latent Dirichlet Allocation for Social Media Based Event Detection and Mapping

C. Ferner^*
, C. Havas
, E. Birnbacher
, S. Wegenkittl
, B. Resch

^*Corresponding author for this work

Department of Geoinformatics – Z_GIS, University of Salzburg
Center for Geographic Analysis, Harvard University

Research output: Contribution to journal › Article › peer-review

Abstract

In the event of a natural disaster, geo-tagged Tweets are an immediate source of information for locating casualties and damages, and for supporting disaster management. Topic modeling can help in detecting disaster-related Tweets in the noisy Twitter stream in an unsupervised manner. However, the results of topic models are difficult to interpret and require manual identification of one or more "disaster topics". Immediate disaster response would benefit from a fully automated process for interpreting the modeled topics and extracting disaster relevant information. Initializing the topic model with a set of seed words already allows to directly identify the corresponding disaster topic. In order to enable an automated end-to-end process, we automatically generate seed words using older Tweets from the same geographic area. The results of two past events (Napa Valley earthquake 2014 and hurricane Harvey 2017) show that the geospatial distribution of Tweets identified as disaster related conforms with the officially released disaster footprints. The suggested approach is applicable when there is a single topic of interest and comparative data available. © 2020 by the authors.

Original language	English
Journal	Information
Volume	11
Issue number	8
DOIs	https://doi.org/10.3390/INFO11080376
Publication status	Published - 25 Jul 2020

Keywords

Disaster management
Geospatial analysis
Social media
Topic modeling
Automation
Disaster prevention
Social networking (online)
Statistics
Comparative data
Disaster response
End-to-end process
Geographic areas
Latent Dirichlet allocation
Manual identification
Natural disasters
Disasters

Access to Document

10.3390/INFO11080376

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089806265&doi=10.3390%2fINFO11080376&partnerID=40&md5=89c512f1be185043094ccec96eef516d

Cite this

@article{6dcf6c10efbc4d95918de3e79acf0f9a,

title = "Automated Seeded Latent Dirichlet Allocation for Social Media Based Event Detection and Mapping",

abstract = "In the event of a natural disaster, geo-tagged Tweets are an immediate source of information for locating casualties and damages, and for supporting disaster management. Topic modeling can help in detecting disaster-related Tweets in the noisy Twitter stream in an unsupervised manner. However, the results of topic models are difficult to interpret and require manual identification of one or more {"}disaster topics{"}. Immediate disaster response would benefit from a fully automated process for interpreting the modeled topics and extracting disaster relevant information. Initializing the topic model with a set of seed words already allows to directly identify the corresponding disaster topic. In order to enable an automated end-to-end process, we automatically generate seed words using older Tweets from the same geographic area. The results of two past events (Napa Valley earthquake 2014 and hurricane Harvey 2017) show that the geospatial distribution of Tweets identified as disaster related conforms with the officially released disaster footprints. The suggested approach is applicable when there is a single topic of interest and comparative data available. {\textcopyright} 2020 by the authors.",

keywords = "Disaster management, Geospatial analysis, Social media, Topic modeling, Automation, Disaster prevention, Social networking (online), Statistics, Comparative data, Disaster response, End-to-end process, Geographic areas, Latent Dirichlet allocation, Manual identification, Natural disasters, Disasters",

author = "C. Ferner and C. Havas and E. Birnbacher and S. Wegenkittl and B. Resch",

note = "Cited By :12 Export Date: 14 December 2023 Correspondence Address: Ferner, C.; Information Technology and Systems Management (ITS), Urstein Sued 1 Puch, Austria; email: [email protected] Correspondence Address: Resch, B.; Department of Geoinformatics-Z\_GIS, Schillerstrasse 30, Austria; email: [email protected] Funding details: 865697 Funding details: Harvard University Funding details: European Regional Development Fund, FEDER, AB215 Funding text 1: This study has been carried out in the HUMAN+ project, which has been funded by the Austrian security research programme KIRAS of the Federal Ministry of Agriculture, Regions and Tourism (BMLRT), project number 865697. Additional funding was granted by the European Regional Development Fund (ERDF) for project number AB215 in the INTERREG program Austria-Bavaria 2014-2020. We would like to thank Harvard University's Center for Geographic Analysis for their support by providing us with the Twitter data for our study. References: Hodge, K., (2020) Techradar 10 News Stories That Broke on Twitter First, , https://www.techradar.com/news/world-of-tech/internet/10-news-stories-that-broke-on-twitter-first-719532, (accessed on 24 July); (2020) Twitter Usage Statistics, , https://www.internetlivestats.com/twitter-statistics/, (accessed on 24 July); Wang, H., Can, D., Kazemzadeh, A., Bar, F., Narayanan, S., A system for real-time twitter sentiment analysis of 2012 us presidential election cycle (2012) Proceedings of the ACL 2012 System Demonstrations, pp. 115-120. , Stroudsburg, PA, USA, 8-14 July; Alsaedi, N., Burnap, P., Rana, O., Can We Predict a Riot? Disruptive Event Detection Using Twitter (2017) ACM Trans. Internet Technol, 17, pp. 1-26; Resch, B., Summa, A., Zeile, P., Strube, M., Citizen-centric Urban Planning through Extracting Emotion Information from Twitter in an Interdisciplinary Space-time-linguistics Algorithm (2016) Urban Plan, 1, pp. 114-127; Niles, M.T., Emery, B.F., Reagan, A.J., Dodds, P.S., Danforth, C.M., Social Media Usage Patterns During Natural Hazards (2019) PLoS ONE, 14; Sakaki, T., Okazaki, M., Matsuo, Y., Earthquake shakes Twitter users: Real-time event detection by social sensors (2010) Proceedings of the 19th international conference on World Wide Web, pp. 851-860. , Raleigh, NC, USA, 26-30 April; Resch, B., People as Sensors and Collective Sensing-contextual Observations Complementing Geo-sensor Network Measurements (2013) Progress in Location-Based Services;, pp. 391-406. , Springer: New York, NY, USA; Havas, C., Resch, B., Francalanci, C., Pernici, B., Scalia, G., Fernandez-Marquez, J., van Achte, T., Grandoni, D., E2mc: Improving Emergency Management Service Practice through Social Media and Crowdsourcing Analysis in Near Real time (2017) Sensors, 17, p. 2766; Blei, D.M., Probabilistic Topic Models (2012) Commun. ACM, 55, pp. 77-84; Chang, J., Gerrish, S., Wang, C., Boyd-Graber, J.L., Blei, D.M., Reading Tea Leaves: How Humans Interpret Topic Models (2009) Advances in Neural Information Processing Systems;, pp. 288-296. , Bengio, Y., Schuurmans, D., Lafferty, J.D., Williams, C.K.I., Culotta, A., Eds.; Curran Associates, Inc.: Red Hook, NY, USA; Li, J., Ge, Y., Hong, Y., Cheema, A., Gu, B., (2017) Textual Review Dimensionality and Helpfulness: A Multi-Method Study, , https://abstract=2931934, (accessed on 18 June 2020); Jagarlamudi, J., Daum{\'e}, H., Udupa, R., Incorporating Lexical Priors into Topic Models (2012) Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 204-213. , Avignon, France, 23-27 April 2012; Association for Computational Linguistics: Stroudsburg, PA, USA; Andrzejewski, D., Zhu, X., Latent Dirichlet Allocation with Topic-in-Set Knowledge (2009) Proceedings of the NAACL HLT 2009 Workshop on Semi-Supervised Learning for Natural Language Processing, pp. 43-48. , Boulder, Colorado, 4 June; Hu, Y., Boyd-Graber, J., Efficient Tree-based Topic Modeling (2012) Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2, pp. 275-279. , Jeju Island, Korea, 8-14 July 2012; Association for Computational Linguistics: Boulder, Colorado; Xie, P., Yang, D., Xing, E., Incorporating Word Correlation Knowledge into Topic Modeling (2015) Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 725-734. , Denver, CO, USA, 31 May-5 June; Guan, X., Chen, C., Using Social Media Data to Understand and Assess Disasters (2014) Nat. Hazards, 74, pp. 837-850; Gr{\"u}nder-Fahrer, S., Schlaf, A., Wiedemann, G., Heyer, G., Topics and topical phases in German social media communication during a disaster (2018) Nat. Lang. Eng, 24, pp. 221-264; Blei, D.M., Ng, A.Y., Jordan, M.I., Latent Dirichlet Allocation (2003) J. Mach. Learn. Res, 3, pp. 993-1022; Hoffman, M., Bach, F.R., Blei, D.M., Online Learning for Latent Dirichlet Allocation (2010) Advances in Neural Information Processing Systems;, pp. 856-864. , Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A., Eds.; Curran Associates, Inc.: Red Hook, NY, USA; Bishop, C.M., (2006) Pattern Recognition and Machine Learning;, , Springer: New York, NY, USA; Mimno, D., Wallach, H.M., Talley, E., Leenders, M., McCallum, A., Optimizing Semantic Coherence in Topic Models (2011) Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 262-272. , Edinburgh, UK, 27-31 July 2011; Association for Computational Linguistics: Stroudsburg, PA, USA; Stevens, K., Kegelmeyer, P., Andrzejewski, D., Buttler, D., Exploring Topic Coherence Over Many Models and Many Topics (2012) Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 952-961. , Jeju Island, Korea, 12-14 July; Wang, S., Chen, Z., Fei, G., Liu, B., Emery, S., Targeted Topic Modeling for Focused Analysis (2016) Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1235-1244. , San Francisco, CA, USA, 13-17 August; Kireyev, K., Palen, L., Anderson, K., Applications of Topics Models to Analysis of Disaster-related Twitter Data (2009) NIPS Workshop on Applications for Topic Models: Text and Beyond;, 1. , JMLR. org: Whistler, BC, Canada; Resch, B., Usl{\"a}nder, F., Havas, C., Combining Machine-learning Topic Models and Spatiotemporal Analysis of Social Media Data for Disaster Footprint and Damage Assessment (2018) Cartogr. Geogr. Inf. Sci, 45, pp. 362-376; Imran, M., Castillo, C., Towards a Data-driven Approach to Identify Crisis-related Topics in Social Media Streams (2015) Proceedings of the 24th ACM International Conference on World Wide Web, pp. 1205-1210. , Florence, Italy, 18-22 May; Blei, D.M., McAuliffe, J.D., Supervised topic models (2007) Proceedings of the 20th International Conference on Neural Information Processing Systems, pp. 121-128. , Vancouver, BC, Canada, 3-7 December; Ashktorab, Z., Brown, C., Nandi, M., Culotta, A., Tweedr: Mining Twitter to Inform Disaster Response (2014) Proceedings of the 11th International Conference on Information Systems for Crisis Response and Management, , University Park, PA, USA, 18-21 May 2014; ISCRAM Association: Centre County, PA, USA; Kirsch, B., Giesselbach, S., Knodt, D., R{\"u}ping, S., Robust End-User-Driven Social Media Monitoring for Law Enforcement and Emergency Monitoring (2018) Community-Oriented Policing and Technological Innovations;, pp. 29-36. , Leventakis, G., Haberfeld, M.R., Eds.; Springer International Publishing: Cham, Switzerland; Yang, M., Mei, J., Ji, H., Zhao, W., Zhao, Z., Chen, X., Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters (2017) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 527-533. , Copenhagen, Denmark, 9-11 September 2017; Association for Computational Linguistics: Copenhagen, Denmark; (2020) Docs-Twitter Developer, , https://developer.twitter.com/en/docs, (accessed on 24 July); Carter, W.N., (2008) Disaster Management: A Disaster Manager's Handbook;, , Asian Development Bank: Metro Manila, Philippines; Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Dubourg, V., Scikit-learn: Machine Learning in Python (2011) J. Mach. Learn. Res, 12, pp. 2825-2830; Denny, M.J., Spirling, A., Text Preprocessing for Unsupervised Learning: Why It Matters, When It Misleads, and What to Do About It (2018) Political Anal, 26, pp. 168-189; Maier, D., Waldherr, A., Miltner, P., Wiedemann, G., Niekler, A., Keinert, A., Pfetsch, B., H{\"a}ussler, T., Applying LDA Topic Modeling in Communication Research: Toward a Valid and Reliable Methodology (2018) Commun. Methods Meas, 12, pp. 93-118; van Oldenborgh, G.J., van der Wiel, K., Sebastian, A., Singh, R., Arrighi, J., Otto, F., Haustein, K., Cullen, H., Attribution of Extreme Rainfall from Hurricane Harvey, August 2017 (2017) Environ. Res. Lett, 12, p. 124009; Lin, T., Tian, W., Mei, Q., Cheng, H., The Dual-sparse Topic Model: Mining Focused Topics and Focused Terms in Short Text (2014) Proceedings of the 23rd ACM International Conference on World Wide Web, pp. 539-550. , Seoul, Korea, 7-11 April; Zhao, W.X., Jiang, J., Weng, J., He, J., Lim, E.P., Yan, H., Li, X., Comparing Twitter and Traditional Media using Topic Models (2011) European Conference on Information Retrieval;, pp. 338-349. , Springer: New York, NY, USA; Manning, C., Raghavan, P., Sch{\"u}tze, H., Introduction to Information Retrieval (2010) Nat. Lang. Eng, 16, pp. 100-103; Wong, D.W.S., Lee, J., (2005) Statistical Analysis of Geographic Information with ArcView GIS and ArcGIS;, , John Wiley \& Sons: Hoboken, NJ, USA; Ord, J.K., Getis, A., Local Spatial Autocorrelation Statistics: Distributional Issues and an Application (1995) Geogr. Anal, 27, pp. 286-306; (2020) Earthquake Hazards Program, , https://earthquake.usgs.gov/earthquakes/eventpage/nc72282711/executive\#general\_executive, (accessed on 18 June); (2020) The Modified Mercalli Intensity Scale, , https://www.usgs.gov/natural-hazards/earthquake-hazards/science/modified-mercalli-intensity-scale?qt-science:center\_objects=0\#qt-science:center\_objects, (accessed on 18 June); (2020) COPERNICUS EMS-Mapping. EMSR229: Hurricane Harvey in Texas, , https://emergency.copernicus.eu/mapping/list-of-components/EMSR229, (accessed on 18 June); Boyd-Graber, J., Blei, D.M., Multilingual Topic Models for Unaligned Text (2009) Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp. 75-82. , Montreal, QC, Canada, 18-21 June 2009; AUAI Press: Arlington, VA, USA; Archive, I., (2020) Archive Team: The Twitter Stream Grab, , https://archive.org/details/twitterstream, (accessed on 24 July); (2020) Twitter Support. Announcement, , https://twitter.com/TwitterSupport/status/1141039841993355264?s=20, (accessed on 24 July); Kumar, A., Singh, J.P., Location Reference Identification from Tweets during Emergencies: A Deep Learning Approach (2019) Int. J. Disaster Risk Reduct, 33, pp. 365-375; Limsopatham, N., Collier, N., Bidirectional LSTM for Named Entity Recognition in Twitter Messages (2016) Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pp. 145-152. , Osaka, Japan, 11 December; Inkpen, D., Liu, J., Farzindar, A., Kazemi, F., Ghazi, D., Location Detection and Disambiguation from Twitter Messages (2017) J. Intell. Inf. Syst, 49, pp. 237-253",

year = "2020",

month = jul,

day = "25",

doi = "10.3390/INFO11080376",

language = "English",

volume = "11",

journal = "Information",

issn = "2078-2489",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "8",

}

TY - JOUR

T1 - Automated Seeded Latent Dirichlet Allocation for Social Media Based Event Detection and Mapping

AU - Ferner, C.

AU - Havas, C.

AU - Birnbacher, E.

AU - Wegenkittl, S.

AU - Resch, B.

N1 - Cited By :12 Export Date: 14 December 2023 Correspondence Address: Ferner, C.; Information Technology and Systems Management (ITS), Urstein Sued 1 Puch, Austria; email: [email protected] Correspondence Address: Resch, B.; Department of Geoinformatics-Z_GIS, Schillerstrasse 30, Austria; email: [email protected] Funding details: 865697 Funding details: Harvard University Funding details: European Regional Development Fund, FEDER, AB215 Funding text 1: This study has been carried out in the HUMAN+ project, which has been funded by the Austrian security research programme KIRAS of the Federal Ministry of Agriculture, Regions and Tourism (BMLRT), project number 865697. Additional funding was granted by the European Regional Development Fund (ERDF) for project number AB215 in the INTERREG program Austria-Bavaria 2014-2020. We would like to thank Harvard University's Center for Geographic Analysis for their support by providing us with the Twitter data for our study. References: Hodge, K., (2020) Techradar 10 News Stories That Broke on Twitter First, , https://www.techradar.com/news/world-of-tech/internet/10-news-stories-that-broke-on-twitter-first-719532, (accessed on 24 July); (2020) Twitter Usage Statistics, , https://www.internetlivestats.com/twitter-statistics/, (accessed on 24 July); Wang, H., Can, D., Kazemzadeh, A., Bar, F., Narayanan, S., A system for real-time twitter sentiment analysis of 2012 us presidential election cycle (2012) Proceedings of the ACL 2012 System Demonstrations, pp. 115-120. , Stroudsburg, PA, USA, 8-14 July; Alsaedi, N., Burnap, P., Rana, O., Can We Predict a Riot? Disruptive Event Detection Using Twitter (2017) ACM Trans. Internet Technol, 17, pp. 1-26; Resch, B., Summa, A., Zeile, P., Strube, M., Citizen-centric Urban Planning through Extracting Emotion Information from Twitter in an Interdisciplinary Space-time-linguistics Algorithm (2016) Urban Plan, 1, pp. 114-127; Niles, M.T., Emery, B.F., Reagan, A.J., Dodds, P.S., Danforth, C.M., Social Media Usage Patterns During Natural Hazards (2019) PLoS ONE, 14; Sakaki, T., Okazaki, M., Matsuo, Y., Earthquake shakes Twitter users: Real-time event detection by social sensors (2010) Proceedings of the 19th international conference on World Wide Web, pp. 851-860. , Raleigh, NC, USA, 26-30 April; Resch, B., People as Sensors and Collective Sensing-contextual Observations Complementing Geo-sensor Network Measurements (2013) Progress in Location-Based Services;, pp. 391-406. , Springer: New York, NY, USA; Havas, C., Resch, B., Francalanci, C., Pernici, B., Scalia, G., Fernandez-Marquez, J., van Achte, T., Grandoni, D., E2mc: Improving Emergency Management Service Practice through Social Media and Crowdsourcing Analysis in Near Real time (2017) Sensors, 17, p. 2766; Blei, D.M., Probabilistic Topic Models (2012) Commun. ACM, 55, pp. 77-84; Chang, J., Gerrish, S., Wang, C., Boyd-Graber, J.L., Blei, D.M., Reading Tea Leaves: How Humans Interpret Topic Models (2009) Advances in Neural Information Processing Systems;, pp. 288-296. , Bengio, Y., Schuurmans, D., Lafferty, J.D., Williams, C.K.I., Culotta, A., Eds.; Curran Associates, Inc.: Red Hook, NY, USA; Li, J., Ge, Y., Hong, Y., Cheema, A., Gu, B., (2017) Textual Review Dimensionality and Helpfulness: A Multi-Method Study, , https://abstract=2931934, (accessed on 18 June 2020); Jagarlamudi, J., Daumé, H., Udupa, R., Incorporating Lexical Priors into Topic Models (2012) Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 204-213. , Avignon, France, 23-27 April 2012; Association for Computational Linguistics: Stroudsburg, PA, USA; Andrzejewski, D., Zhu, X., Latent Dirichlet Allocation with Topic-in-Set Knowledge (2009) Proceedings of the NAACL HLT 2009 Workshop on Semi-Supervised Learning for Natural Language Processing, pp. 43-48. , Boulder, Colorado, 4 June; Hu, Y., Boyd-Graber, J., Efficient Tree-based Topic Modeling (2012) Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2, pp. 275-279. , Jeju Island, Korea, 8-14 July 2012; Association for Computational Linguistics: Boulder, Colorado; Xie, P., Yang, D., Xing, E., Incorporating Word Correlation Knowledge into Topic Modeling (2015) Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 725-734. , Denver, CO, USA, 31 May-5 June; Guan, X., Chen, C., Using Social Media Data to Understand and Assess Disasters (2014) Nat. Hazards, 74, pp. 837-850; Gründer-Fahrer, S., Schlaf, A., Wiedemann, G., Heyer, G., Topics and topical phases in German social media communication during a disaster (2018) Nat. Lang. Eng, 24, pp. 221-264; Blei, D.M., Ng, A.Y., Jordan, M.I., Latent Dirichlet Allocation (2003) J. Mach. Learn. Res, 3, pp. 993-1022; Hoffman, M., Bach, F.R., Blei, D.M., Online Learning for Latent Dirichlet Allocation (2010) Advances in Neural Information Processing Systems;, pp. 856-864. , Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A., Eds.; Curran Associates, Inc.: Red Hook, NY, USA; Bishop, C.M., (2006) Pattern Recognition and Machine Learning;, , Springer: New York, NY, USA; Mimno, D., Wallach, H.M., Talley, E., Leenders, M., McCallum, A., Optimizing Semantic Coherence in Topic Models (2011) Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 262-272. , Edinburgh, UK, 27-31 July 2011; Association for Computational Linguistics: Stroudsburg, PA, USA; Stevens, K., Kegelmeyer, P., Andrzejewski, D., Buttler, D., Exploring Topic Coherence Over Many Models and Many Topics (2012) Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 952-961. , Jeju Island, Korea, 12-14 July; Wang, S., Chen, Z., Fei, G., Liu, B., Emery, S., Targeted Topic Modeling for Focused Analysis (2016) Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1235-1244. , San Francisco, CA, USA, 13-17 August; Kireyev, K., Palen, L., Anderson, K., Applications of Topics Models to Analysis of Disaster-related Twitter Data (2009) NIPS Workshop on Applications for Topic Models: Text and Beyond;, 1. , JMLR. org: Whistler, BC, Canada; Resch, B., Usländer, F., Havas, C., Combining Machine-learning Topic Models and Spatiotemporal Analysis of Social Media Data for Disaster Footprint and Damage Assessment (2018) Cartogr. Geogr. Inf. Sci, 45, pp. 362-376; Imran, M., Castillo, C., Towards a Data-driven Approach to Identify Crisis-related Topics in Social Media Streams (2015) Proceedings of the 24th ACM International Conference on World Wide Web, pp. 1205-1210. , Florence, Italy, 18-22 May; Blei, D.M., McAuliffe, J.D., Supervised topic models (2007) Proceedings of the 20th International Conference on Neural Information Processing Systems, pp. 121-128. , Vancouver, BC, Canada, 3-7 December; Ashktorab, Z., Brown, C., Nandi, M., Culotta, A., Tweedr: Mining Twitter to Inform Disaster Response (2014) Proceedings of the 11th International Conference on Information Systems for Crisis Response and Management, , University Park, PA, USA, 18-21 May 2014; ISCRAM Association: Centre County, PA, USA; Kirsch, B., Giesselbach, S., Knodt, D., Rüping, S., Robust End-User-Driven Social Media Monitoring for Law Enforcement and Emergency Monitoring (2018) Community-Oriented Policing and Technological Innovations;, pp. 29-36. , Leventakis, G., Haberfeld, M.R., Eds.; Springer International Publishing: Cham, Switzerland; Yang, M., Mei, J., Ji, H., Zhao, W., Zhao, Z., Chen, X., Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters (2017) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 527-533. , Copenhagen, Denmark, 9-11 September 2017; Association for Computational Linguistics: Copenhagen, Denmark; (2020) Docs-Twitter Developer, , https://developer.twitter.com/en/docs, (accessed on 24 July); Carter, W.N., (2008) Disaster Management: A Disaster Manager's Handbook;, , Asian Development Bank: Metro Manila, Philippines; Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Dubourg, V., Scikit-learn: Machine Learning in Python (2011) J. Mach. Learn. Res, 12, pp. 2825-2830; Denny, M.J., Spirling, A., Text Preprocessing for Unsupervised Learning: Why It Matters, When It Misleads, and What to Do About It (2018) Political Anal, 26, pp. 168-189; Maier, D., Waldherr, A., Miltner, P., Wiedemann, G., Niekler, A., Keinert, A., Pfetsch, B., Häussler, T., Applying LDA Topic Modeling in Communication Research: Toward a Valid and Reliable Methodology (2018) Commun. Methods Meas, 12, pp. 93-118; van Oldenborgh, G.J., van der Wiel, K., Sebastian, A., Singh, R., Arrighi, J., Otto, F., Haustein, K., Cullen, H., Attribution of Extreme Rainfall from Hurricane Harvey, August 2017 (2017) Environ. Res. Lett, 12, p. 124009; Lin, T., Tian, W., Mei, Q., Cheng, H., The Dual-sparse Topic Model: Mining Focused Topics and Focused Terms in Short Text (2014) Proceedings of the 23rd ACM International Conference on World Wide Web, pp. 539-550. , Seoul, Korea, 7-11 April; Zhao, W.X., Jiang, J., Weng, J., He, J., Lim, E.P., Yan, H., Li, X., Comparing Twitter and Traditional Media using Topic Models (2011) European Conference on Information Retrieval;, pp. 338-349. , Springer: New York, NY, USA; Manning, C., Raghavan, P., Schütze, H., Introduction to Information Retrieval (2010) Nat. Lang. Eng, 16, pp. 100-103; Wong, D.W.S., Lee, J., (2005) Statistical Analysis of Geographic Information with ArcView GIS and ArcGIS;, , John Wiley & Sons: Hoboken, NJ, USA; Ord, J.K., Getis, A., Local Spatial Autocorrelation Statistics: Distributional Issues and an Application (1995) Geogr. Anal, 27, pp. 286-306; (2020) Earthquake Hazards Program, , https://earthquake.usgs.gov/earthquakes/eventpage/nc72282711/executive#general_executive, (accessed on 18 June); (2020) The Modified Mercalli Intensity Scale, , https://www.usgs.gov/natural-hazards/earthquake-hazards/science/modified-mercalli-intensity-scale?qt-science:center_objects=0#qt-science:center_objects, (accessed on 18 June); (2020) COPERNICUS EMS-Mapping. EMSR229: Hurricane Harvey in Texas, , https://emergency.copernicus.eu/mapping/list-of-components/EMSR229, (accessed on 18 June); Boyd-Graber, J., Blei, D.M., Multilingual Topic Models for Unaligned Text (2009) Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp. 75-82. , Montreal, QC, Canada, 18-21 June 2009; AUAI Press: Arlington, VA, USA; Archive, I., (2020) Archive Team: The Twitter Stream Grab, , https://archive.org/details/twitterstream, (accessed on 24 July); (2020) Twitter Support. Announcement, , https://twitter.com/TwitterSupport/status/1141039841993355264?s=20, (accessed on 24 July); Kumar, A., Singh, J.P., Location Reference Identification from Tweets during Emergencies: A Deep Learning Approach (2019) Int. J. Disaster Risk Reduct, 33, pp. 365-375; Limsopatham, N., Collier, N., Bidirectional LSTM for Named Entity Recognition in Twitter Messages (2016) Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pp. 145-152. , Osaka, Japan, 11 December; Inkpen, D., Liu, J., Farzindar, A., Kazemi, F., Ghazi, D., Location Detection and Disambiguation from Twitter Messages (2017) J. Intell. Inf. Syst, 49, pp. 237-253

PY - 2020/7/25

Y1 - 2020/7/25

N2 - In the event of a natural disaster, geo-tagged Tweets are an immediate source of information for locating casualties and damages, and for supporting disaster management. Topic modeling can help in detecting disaster-related Tweets in the noisy Twitter stream in an unsupervised manner. However, the results of topic models are difficult to interpret and require manual identification of one or more "disaster topics". Immediate disaster response would benefit from a fully automated process for interpreting the modeled topics and extracting disaster relevant information. Initializing the topic model with a set of seed words already allows to directly identify the corresponding disaster topic. In order to enable an automated end-to-end process, we automatically generate seed words using older Tweets from the same geographic area. The results of two past events (Napa Valley earthquake 2014 and hurricane Harvey 2017) show that the geospatial distribution of Tweets identified as disaster related conforms with the officially released disaster footprints. The suggested approach is applicable when there is a single topic of interest and comparative data available. © 2020 by the authors.

AB - In the event of a natural disaster, geo-tagged Tweets are an immediate source of information for locating casualties and damages, and for supporting disaster management. Topic modeling can help in detecting disaster-related Tweets in the noisy Twitter stream in an unsupervised manner. However, the results of topic models are difficult to interpret and require manual identification of one or more "disaster topics". Immediate disaster response would benefit from a fully automated process for interpreting the modeled topics and extracting disaster relevant information. Initializing the topic model with a set of seed words already allows to directly identify the corresponding disaster topic. In order to enable an automated end-to-end process, we automatically generate seed words using older Tweets from the same geographic area. The results of two past events (Napa Valley earthquake 2014 and hurricane Harvey 2017) show that the geospatial distribution of Tweets identified as disaster related conforms with the officially released disaster footprints. The suggested approach is applicable when there is a single topic of interest and comparative data available. © 2020 by the authors.

KW - Disaster management

KW - Geospatial analysis

KW - Social media

KW - Topic modeling

KW - Automation

KW - Disaster prevention

KW - Social networking (online)

KW - Statistics

KW - Comparative data

KW - Disaster response

KW - End-to-end process

KW - Geographic areas

KW - Latent Dirichlet allocation

KW - Manual identification

KW - Natural disasters

KW - Disasters

U2 - 10.3390/INFO11080376

DO - 10.3390/INFO11080376

M3 - Article

SN - 2078-2489

VL - 11

JO - Information

JF - Information

IS - 8

ER -

Automated Seeded Latent Dirichlet Allocation for Social Media Based Event Detection and Mapping

Abstract

Keywords

Access to Document

Fingerprint

Cite this