research-article

Combining Automatic and Manual Approaches: Towards a Framework for Discovering Themes in Disaster-related Tweets

Authors:

Leif Romeritch Syliongka,

Cheryll Ruth Soriano,

Ma. Divina Gracia Roldan,

Francisco Magno,

Charibeth ChengAuthors Info & Claims

WWW '15 Companion: Proceedings of the 24th International Conference on World Wide Web

Pages 1239 - 1244

https://doi.org/10.1145/2740908.2742125

Published: 18 May 2015 Publication History

Abstract

In this paper, we present a framework that combines automatic and manual approaches to discover themes in disaster-related tweets. As case study, we decided to focus on tweets related to typhoon Haiyan, which caused billions of dollars in damages. We collected tweets from November 2013 to March 2014 and used the local typhoon name "Yolanda" as the filter. Data association was used to expand the tweet set and k-means clustering was then applied. Clusters with high number of instances were subjected to open coding for labeling. The Silhouette indices ranged from 0.27 to 0.50. Analyses reveal that the use of automated Natural Language Processing (NLP) approach has the potential to deal with huge volumes of tweets by clustering frequently occurring words and phrases. This complements the manual approach to surface themes from a more manageable set of tweet pool, allowing for a more nuanced analysis of tweets from a human expert. As application, the themes identified during open coding were used as labels to train a classifier system. Future work could explore on using topic models and focusing on specific content or issues, such as natural calamities and citizen's participation in addressing these.

References

[1]

Agrawal, R., T. Imielinski, and A. Swami. 1993. Mining Association Rules between Sets of Items in Large Databases. In Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data.

Digital Library

[2]

Beduya, L. J. and K. J. Espinosa. 2014. Flood-Related Disaster Tweet Classification Using Support Vector Machines. Proceedings of the 10th National Natural Language Processing Research Symposium.

[3]

Caragea, C., N. McNeese, A. Jaiswal, G. Traylor, H.-W. Kim, P. Mitra, D. Wu, A. Tapia, L. Giles, B. Jansen, and J. Yen. 2011. Classifying Text Messages for Haiti Earthquake. 8th International Conference on Information Systems for Crisis Response and Management.

[4]

Centeno, D. 2010. Celebrification in Philippine Politics: Exploring the Relationship Between Celebrity Endorsers? Parasociability and the Public Voting Behavior. Social Science Diliman,6(1): 66--85.

[5]

De Vicente, J., J. Lanchares, and R. Hermida. 2003. Placement by Thermodynamic Simulated Annealing. Physics Letters A, 317(5-6): 415--423.

[6]

Feldman, R. 2013. Techniques and Applications for Sentiment Analysis. Communications of the ACM, 56(4): 82--89.

Digital Library

[7]

Freeman, M. 2011. Fire, Wind and Water: Social Networks in Natural Disasters. Journal of Cases on Information Technology, 13(2): 69--79.

Digital Library

[8]

Glaser, B. 1978. The Grounded Theory Perspective II: Description's Remodeling of Grounded Theory Methodology. The Sociology Press, CA.

[9]

Gonzales, H. A. and K. J. Espinosa. 2014. Community Structure Detection and Analysis in Disaster Related Tweets. Proceedings of the 10th National Natural Language Processing Research Symposium.

[10]

Hartigan, J. A. and M. A. Wong. 1979. Algorithm AS 136: A K-Means Clustering Algorithm. Journal of the Royal Statistical Society, Series C, 28(1): 100--108.

[11]

Hartley, J. 2008. Television Truths: Forms of Knowledge in Popular Culture. Wiley-Blackwell, Malden, MA.

[12]

Heverin, T. and L. Zach. 2010. Twitter for City Police Department Information Sharing. Proceedings of the 73rd American Society for Information Science and Technology Conference.

Digital Library

[13]

Honeycutt, C. and S. Herring. 2009. Beyond Microblogging: Conversation and Collaboration via Twitter. Proceedings of the 42nd Hawaii International Conference on System Sciences.

Digital Library

[14]

Imran, M., C. Castillo, F. Diaz, and S. Vieweg. 2012. Processing Social Media Messages in Mass Emergency: A Survey. arXiv.org. Available: http://arxiv.org/abs/1407.7071

[15]

Imran, M., C. Castillo, J. Lucas, P. Meier, and S. Vieweg. AIDR: Artificial intelligence for disaster response. 2014. In Proceedings of the Companion Publication of the 23rd International Conference on World Wide Web.

Digital Library

[16]

Jansen, B., M. Zhang, K. Sobel, and A. Chowdury. 2009. Twitter Power: Tweets as Electronic Word of Mouth. Journal of the American Society for Information Science and Technology archive, 60(11): 2169--2188.

Digital Library

[17]

Kaufman, L. and P. Rousseeuw. 1990. Finding Groups in Data -- An Introduction to Cluster Analysis. Probability and Mathematical Statistics. John Wiley and Sons, Inc., NY.

[18]

Koehn, P., H. Hoang, A. Birch, C. Callison-Burch, M. Federico, N. Bertoldi, B. Cowan, W. Shen, C. Moran, R. Zens, C. Dyer, O. Bojar, A. Constantin, and E. Herbst. 2007. Moses: Open Source Toolkit for Statistical Machine Translation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Demonstration Session.

Digital Library

[19]

Lam, A.J., I. Paner, J. M. Macatangay, D.D. Delos Santos. 2014. Classifying Typhoon Related Tweets. Proceedings of the 10th National Natural Language Processing Research Symposium.

[20]

Li, J. and H.R. Rao. 2010. Twitter as a Rapid Response News Service: An Exploration in the Context of the 2008 China Earthquake. The Electronic Journal on Information Systems in Developing Countries, 42(4): 1--22.

[21]

Manning, C., P. Raghavan, and H. Schütze. 2008. Introduction to Information Retrieval. Cambridge University Press, Cambridge, UK.

Digital Library

[22]

Metaxas, P., E. Mustafaraj, and D. Gayo-Avello. How (Not) To Predict Elections. Proceedings of the 3rd IEEE International Conference on Social Computing and the 3rd IEEE International Conference on Privacy, Security, Risk and Trust.

[23]

Meier, P. 2012. How the UN Used Social Media in Response to Typhoon Pablo (Updated). iRevolutions: From innovation to Revolutions. Available: http://irevolution.net/2012/12/08/digital-response-typhoon-pablo/

[24]

Morales, X.Y.Z. 2010. Networks to the Rescue Tweeting Aid and Relief During Ondoy. M.A. Thesis, Georgetown University.

[25]

Neuman, W.R., L. Guggenheim, S. Mo Jang, and S. Young Bae. 2014. The Dynamics of Public Attention: Agenda Setting Meets Big Data. Journal of Communication, 64(2): 193--214.

[26]

Oco, N. and R. E. Roxas. 2012. Pattern Matching Refinements to Dictionary-Based Code-Switching Point Detection. In Proceedings of the 26th Pacific Asia Conference on Language, Information, and Computation.

[27]

Oco, N., L. R. Syliongka, J. Ilao, and R. E. Roxas. 2013. Dice's Coefficient on Trigram Profiles as Metric for Language Similarity. In Proceedings of the 16th Oriental COCOSDA.

[28]

Pablo, Z.C., N. Oco, M. D. G. Roldan, C. Cheng, and R. E. Roxas. Toward an Enriched Understanding of Factors Influencing Filipino Behavior during Elections through the Analysis of Twitter Data. Philippine Political Science Journal, 35(2): 203--224.

[29]

Parks, M. 2014. Big Data in Communication Research: Its Contents, and Discontents. Journal of Communication, 64(2): 355--360.

[30]

Rajaraman, A. and J. D. Ullman. 2011. Mining of Massive Datasets. Cambridge University Press, Cambridge, UK.

Digital Library

[31]

Richards, L. 2005. Handling Qualitative Data: A Practical Guide. Sage, London.

[32]

Skinner, J. 2013. Natural Disasters and Twitter: Thinking from both sides of the Tweet. First Monday, 18(9).

[33]

Smith, B. 2010. Socially Distributing Public Relations: Twitter, Haiti, and Interactivity in Social Media. Public Relations Review, 36(4): 329--335.

[34]

Syliongka, L.R. and N. Oco. 2014. Using Language Modeling and Data Association to Perform Named Entity Recognition. Proceedings of the 10th National Natural Language Processing Research Symposium.

[35]

Tumasjan, A., T. Sprenger, P. Sandner, I. Welpe. 2011. Election Forecasts With Twitter: How 140 Characters Reflect the Political Landscape. Social Science Computer Review, 29(4): 402--418.

Digital Library

[36]

Vargo, C., L. Guo, M. McCombs, and D. Shaw. 2014. Network Issue Agendas on Twitter During the 2012 Presidential Elections. Journal of Communication, 64(2): 296--316.

[37]

Verbeke, M., B. Berendt, L. d'Haenens, and M. Opgenhaffen. 2014. When Two Disciplines Meet, Data Mining for Communication Science. Proceedings of the 2014 Annual Meeting of International Communication Association.

[38]

Yin, J., A. Lampert, M. Cameron, B. Robinson, and R. Power. 2012. Using Social Media to Enhance Emergency Situation Awareness. IEEE Intelligent Systems, 27(6): 52--59.

Digital Library

Cited By

Acosta MPalaoag T(2019)Characterization of Disaster Related Tweets According to Its UrgencyProceedings of the 2019 5th International Conference on Computing and Artificial Intelligence10.1145/3330482.3330498(30-37)Online publication date: 19-Apr-2019
https://dl.acm.org/doi/10.1145/3330482.3330498
Lam AOco NRoxas R(2017)Towards the development of typhoon-related tweet classifiers despite the sparseness of strongly-annotated dataTENCON 2017 - 2017 IEEE Region 10 Conference10.1109/TENCON.2017.8228265(2409-2414)Online publication date: Nov-2017
https://doi.org/10.1109/TENCON.2017.8228265
Ancheta JSy CMaceda LOco NRoxas R(2017)Computer-assisted thematic analysis of Typhoon Fung-Wong tweetsTENCON 2017 - 2017 IEEE Region 10 Conference10.1109/TENCON.2017.8227955(723-726)Online publication date: Nov-2017
https://doi.org/10.1109/TENCON.2017.8227955
Show More Cited By

Index Terms

Combining Automatic and Manual Approaches: Towards a Framework for Discovering Themes in Disaster-related Tweets
1. Information systems
  1. Information retrieval
    1. Retrieval tasks and goals
      1. Clustering and classification
  2. Information systems applications
    1. Data mining
      1. Clustering

Recommendations

Twitter Flu Trend: A Hybrid Deep Neural Network for Tweet Analysis
Artificial Intelligence XXXIX
Abstract
Popular social networks such as Twitter have been proposed as a data source for public health monitoring because they have the potential to show infection disease surveillance like Influenza-Like Illnesses (ILI). However, shortness, data sparsity, ...
French presidential elections: what are the most efficient measures for tweets?
PLEAD '12: Proceedings of the first edition workshop on Politics, elections and data

Tweets exchanged over the Internet are an important source of information even if their characteristics make them difficult to analyze (e.g., a maximum of 140 characters; noisy data). In this paper, we address the problem of extracting relevant topics ...
Forecasting COVID-19 Vaccination Rates using Social Media Data
WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023

The COVID-19 pandemic has had a profound impact on the global community, and vaccination has been recognized as a crucial intervention. To gain insight into public perceptions of COVID-19 vaccines, survey studies and the analysis of social media ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

WWW '15 Companion: Proceedings of the 24th International Conference on World Wide Web

May 2015

1602 pages

ISBN:9781450334730

DOI:10.1145/2740908

General Chairs:
Aldo Gangemi
National Research Council, Italy & Paris 13 University-CNRS, France
,
Stefano Leonardi
Sapienza University of Rome, Italy
,
Alessandro Panconesi
Sapienza University of Rome, Italy

Copyright © 2015 Copyright is held by the International World Wide Web Conference Committee (IW3C2).

Sponsors

IW3C2: International World Wide Web Conference Committee

In-Cooperation

SIGWEB: ACM Special Interest Group on Hypertext, Hypermedia, and Web

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 18 May 2015

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

University Research Coordination Office of De La Salle University

Conference

WWW '15

Sponsor:

IW3C2

WWW '15: 24th International World Wide Web Conference

May 18 - 22, 2015

Florence, Italy

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
135
Total Downloads

Downloads (Last 12 months)6
Downloads (Last 6 weeks)2

Reflects downloads up to 25 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Acosta MPalaoag T(2019)Characterization of Disaster Related Tweets According to Its UrgencyProceedings of the 2019 5th International Conference on Computing and Artificial Intelligence10.1145/3330482.3330498(30-37)Online publication date: 19-Apr-2019
https://dl.acm.org/doi/10.1145/3330482.3330498
Lam AOco NRoxas R(2017)Towards the development of typhoon-related tweet classifiers despite the sparseness of strongly-annotated dataTENCON 2017 - 2017 IEEE Region 10 Conference10.1109/TENCON.2017.8228265(2409-2414)Online publication date: Nov-2017
https://doi.org/10.1109/TENCON.2017.8228265
Ancheta JSy CMaceda LOco NRoxas R(2017)Computer-assisted thematic analysis of Typhoon Fung-Wong tweetsTENCON 2017 - 2017 IEEE Region 10 Conference10.1109/TENCON.2017.8227955(723-726)Online publication date: Nov-2017
https://doi.org/10.1109/TENCON.2017.8227955
De La Cruz AOco NRoxas R(2017)A classifier module for analyzing community responses on disaster preparedness2017IEEE 9th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM)10.1109/HNICEM.2017.8269532(1-5)Online publication date: Dec-2017
https://doi.org/10.1109/HNICEM.2017.8269532
Legaspi RNarararatwong RCooharojananone NOkada HMaruyama H(2016)Perception-Based Resilience: Accounting for Human Perception in Resilience Thinking with Its Theoretic and Model BasesUrban Resilience10.1007/978-3-319-39812-9_6(95-114)Online publication date: 11-Aug-2016
https://doi.org/10.1007/978-3-319-39812-9_6

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents