The science behind AIDR

AIDR is based on supervised machine learning, and described in the following papers and presentations:

• Firoj Alam, Shafiq Joty, Muhammad Imran. Domain Adaptation with Adversarial Training and Graph Embeddings. In proceedings of the the 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018, Melbourne, Australia. (arxiv preprint)

• Koustav Rudra, Niloy Ganguly, Pawan Goyal, Prasenjit Mitra, Muhammad Imran. Identifying Sub-events and Summarizing Disaster-Related Information from Microblogs. In proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2018, Michigan, USA. (acm | dataset | code)

• Himanshu Zade, Kushal Shah, Vaibhavi Rangarajann, Priyanka Kshirsagar, Muhammad Imran, Kate Starbird: From Situational Awareness to Actionability: Towards Improving the Utility of Social Media Data for Crisis Response. In proceedings of the 21st ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW), 2018, New York, USA.

• Firoj Alam, Ferda Ofli, Muhammad Imran. Processing Social Media Images by Combining Human and Machine Computing During Crises. In the International Journal of Human-Computer Interaction (IJHCI), 2018. (Taylor & Francies Online | DOI)

• Hemant Purohit, Carlos Castillo, Muhammad Imran and Rahul Pandey: Social-EOC: Serviceability Model to Rank Social Media Requests for Emergency Operation Centers. In proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Barcelona, August 2018.

• Hemant Purohit, Carlos Castillo, Muhammad Imran and Rahul Pandey: Ranking of Social Media Alerts with Workload Bounds in Emergency Operation Centers. To appear in ACM/IEEE Web Intelligence, Santiago, Chile, December 2018.

• Xukun Li, Huaiyu Zhang, Doina Caragea, Muhammad Imran: Localizing and Quantifying Damage in Social Media Images.In proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Barcelona, August 2018. (arXiv)

• Luis Fernandez-Luque, Muhammad Imran. Humanitarian Health Computing using Artificial Intelligence and Social Media: A Narrative Literature Review. In the International Journal of Medical Informatics (IJMI), 2018. (ScienceDirect | DOI)

• Koustav Rudra, Ashish Sharma, Niloy Ganguly, Muhammad Imran. Classifying and Summarizing Information from Microblogs during Epidemics. In the Journal of Information Systems Frontiers, Springer, 2018.

• Muhammad Imran, Carlos Castillo, Fernando Diaz, Sarah Vieweg. Processing Social Media Messages in Mass Emergency: Survey Summary. In proceedings of the Web Conference (WWW), April 2018, Lyon, France. (acm | slides)

• Firoj Alam, Shafiq Joty, Muhammad Imran. Graph Based Semi-supervised Learning with Convolutional Neural Networks to Classify Crisis Related Tweets. In proceedings of the International AAAI Conference on Web and Social Media (ICWSM), 2018, Stanford, California, USA. (arxiv preprint)

• Firoj Alam, Ferda Ofli and Muhammad Imran. CrisisMMD: Multimodal Twitter Datasets from Natural Disasters. In proceedings of the International AAAI Conference on Web and Social Media (ICWSM), 2018, Stanford, California, USA. (Dataset)

• Firoj Alam, Ferda Ofli, Muhammad Imran, Michael Aupetit. A Twitter Tale of Three Hurricanes: Harvey, Irma, and Maria. In proceedings of the 15th International Conference on Information Systems for Crisis Response and Management (ISCRAM), May 2018, Rochester NY, USA. (arxiv preprint | Dataset)

• Reza Mazloom, HongMin Li, Doina Caragea, Muhammad Imran, Cornelia Caragea. Classification of Twitter Disaster Data Using a Hybrid Feature-Instance Adaptation Approach. In proceedings of the 15th International Conference on Information Systems for Crisis Response and Management (ISCRAM), May 2018, Rochester NY, USA.

• Kiran Zahra, Muhammad Imran, Frank O. Ostermann. Understanding Eyewitness Reports on Twitter during Disasters. In proceedings of the 15th International Conference on Information Systems for Crisis Response and Management (ISCRAM), May 2018, Rochester NY, USA.

• Christian Reuter, Amanda Hughes, Starr Roxanne Hiltz, Muhammad Imran, Linda Plotnick. Editorial of the Special Issue on Social Media in Crisis Management. In the International Journal of Human-Computer Interaction (IJHCI), 2018. (Taylor & Francies Online | DOI)

• Muhammad Imran, Patrick Meier, Kees Boersma. Big Data Surveillance and Crisis Management. Edited by: Kees Boersma and Chiara Fonio, Published by: Routledge, ISBN: 978-1-138-19543-1, 2017.

• Firoj Alam, Muhammad Imran, Ferda Ofli. Image4Act: Online Social Media Image Processing for Disaster Response. In Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2017, Sydney, Australia.

• Dat Tien Nguyen, Ferda Ofli, Muhammad Imran, Prasenjit Mitra. Damage Assessment from Social Media Imagery Data During Disasters. In Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2017, Sydney, Australia.

• Firoj Alam, Muhammad Imran, Ferda Ofli. Online Social Media Image Processing Using AIDR 2.0: Artificial Intelligence for Digital Response. Demoed at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Honolulu, Hawaii.

• Muhammad Imran, Firoj Alam, Ferda Ofli, Michael Aupetit. Enabling Rapid Disaster Response Using Artificial Intelligence and Social Media. International Roundtable on the Impacts of Extreme Natural Events: Science and Technology for Mitigation (IRENE) workshop, December 2017, Colombo, Sri Lanka.

• Dat Tien Nguyen, Kamela Ali Al Mannai, Shafiq Joty, Hassan Sajjad, Muhammad Imran, Prasenjit Mitra. Robust Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks. In Proceedings of the 11th International AAAI Conference on Web and Social Media (ICWSM), 2017, Montreal, Canada.

• Koustav Rudra, Ashish Sharma, Niloy Ganguly, Muhammad Imran. Classifying Information from Microblogs During Epidemics. In proceedings of the ACM Digital Health (DH) Conference, 2017, London, United Kingdom.

• Dat Tien Nguyen, Firoj Alam, Ferda Ofli, Muhammad Imran. Automatic Image Filtering on Social Networks Using Deep Learning and Perceptual Hashing During Crises. In Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (ISCRAM), 2017 Albi, France. (Slides)

• Michael Aupetit, Muhammad Imran. Interactive Monitoring of Critical Situational Information on Social Media. In Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (ISCRAM), 2017 Albi, France.

• Muhammad Imran, Prasenjit Mitra, Jaideep Srivastava. Enabling Rapid Classification of Social Media Communications During Crises. In the International Journal of Information Systems for Crisis Response and Management, 2017. DOI: 10.4018/IJISCRAM.2016070101.

• Zoha Sheikh, Hira Masood, Sharifullah Khan, Muhammad Imran. User-Assisted Information Extraction from Twitter During Emergencies. In Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (ISCRAM), 2017 Albi, France.

• Muhammad Imran, Sanjay Chawla, Carlos Castillo. A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting. In Proceedings of the 18th International Conference on Data Mining (ICDM), December 2016, Barcelona, Spain. (slides|arXiv)

• Koustav Rudra, Siddhartha Banerjee, Niloy Ganguly, Pawan Goyal, Muhammad Imran and Prasenjit Mitra. Summarizing Situational and Topical Information During Crises. Accepted for publication at the 4th international workshop on Social Web for Disaster Management (SWDM), co-located with CIKM, October, 2016, Indianapolis, USA.

• Dat Tien Nguyen, Kamela Ali Al Mannai, Shafiq Joty, Hassan Sajjad, Muhammad Imran, Prasenjit Mitra. Rapid Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks. arXiv:1608.03902, 2016. (arXiv)

• [BEST PAPER AWARD] - Muhammad Imran, Prasenjit Mitra, Jaideep Srivastava. Cross-Language Domain Adaptation for Classifying Crisis-Related Short Messages. In Proceedings of the 13th International Conference on Information Systems for Crisis Response and Management (ISCRAM), 2016, Rio de Janeiro, Brazil.

• Dat Tien Nguyen, Shafiq Joty, Muhammad Imran, Hassan Sajjad, Prasenjit Mitra. Applications of Online Deep Learning for Crisis Response Using Social Media Information. Accepted at the 4th international workshop on Social Web for Disaster Management (SWDM), co-located with CIKM, October, 2016, Indianapolis, USA. (arXiv)

• Koustav Rudra, Siddhartha Banerjee, Niloy Ganguly, Pawan Goyal, Muhammad Imran and Prasenjit Mitra. Summarizing Situational Tweets in Crisis Scenario. In Proceedings of the 27th ACM Conference on Hypertext and Social Media (HT), July 2016, Halifax, Canada. (slides)

• Muhammad Imran, Prasenjit Mitra, Carlos Castillo. Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages. In Proceedings of the 10th Language Resources and Evaluation Conference (LREC), 2016, Slovenia.(Datasets)

• Muhammad Imran, Patrick Meier, Carlos Castillo, Andre Lesa, and Manuel Garcia Herranz. Enabling Digital Health by Automatic Classification of Short Messages. In Proceedings of the 6th ACM International Conference on Digital Health (DH), 2016, Montreal, Canada. (Featured in New Scientist | acm | arXiv)

• Ferda Ofli, Patrick Meier, Muhammad Imran, Carlos Castillo, Devis Tuia, Nicolas Rey, Julien Briant, Pauline Millet, Friedrich Reinhard, Matthew Parkan, and Stephane Joost. Combining Human Computing and Machine Learning to Make Sense of Big (Aerial) Data for Disaster Response. Big Data Journal, March 2016. (liebert)

• [Book Chapter] Carlos Castillo, Muhammad Imran, Patrick Meier, Ji Kim Lucas, Jaideep Srivastava, Heather Leson, Ferda Ofli, Prasenjit Mitra, et al. Together We Stand---Supporting Decision in Crisis Response: Artificial Intelligence for Digital Response and MicroMappers. Edited by OCHA and partners. Published by: Tudor Rose, World Humanitarian Summit, Istanbul, pp. 93-95, ISBN: 978-0-9568561-8-0, May 2016.

• Muhammad Imran, Carlos Castillo, Fernando Diaz, Sarah Vieweg: Processing Social Media Messages in Mass Emergency: A Survey. ACM Computing Surveys. 47, 4, Article 67, June 2015. (acm | arXiv)

• Muhammad Imran, Ioanna Lykourentzou, Yannick Naudet, and Carlos Castillo. Engineering Crowdsourced Stream Processing Systems. Preprint, arXiv:1310.5463.

• Muhammad Imran and Carlos Castillo.Towards a Data-driven Approach to Identify Crisis-Related Topics in Social Media Streams. Social Web for Disaster Management(SWDM) - Co-located with WWW, 2015, Florence, Italy. (slides)

• Soudip Roy Chowdhury, Hemant Purohit and Muhammad Imran. D-Sieve: A Novel Data Processing Engine for Efficient Handling of Crises-Related Social Messages. Social Web for Disaster Management (SWDM) - Co-located with WWW, 2015, Florence, Italy. (slides)

• Muhammad Imran, Carlos Castillo, Ji Lucas, Patrick Meier, and Sarah Vieweg. AIDR: Artificial Intelligence for Disaster Response. In Proc. of the 23th International Conference on World Wide Web (WWW) Companion, 2014. Seoul, Korea.

• Muhammad Imran, Carlos Castillo, Ji Lucas, Patrick Meier, and Jakob Rogstadius. Coordinating Human and Machine Intelligence to Classify Microblog Communications in Crises. In Proc. of the 11th International Conference on Information Systems for Crisis Response and Management (ISCRAM), 2014. Pennsylvania, USA.

• Sarah Vieweg, Carlos Castillo and Muhammad Imran: Integrating Social Media Communications into the Rapid Assessment of Sudden Onset Disasters. In Proc. of The 6th International Conference on Social Informatics (SocInfo), 2014, Barcelona, Spain.

• Muhammad Moeen Uddin, Muhammad Imran, Hassan Sajjad. Understanding Types of Users on Twitter. In SocialCom Stanford Conference 2014, CA, USA.

• Muhammad Imran and Carlos Castillo. Volunteer-powered Automatic Classification of Social Media Messages for Public Health in AIDR. Public Health in the Digital Age workshop - Co-located with WWW, 2014, Seoul, Korea.

• [BEST PAPER AWARD] - Muhammad Imran, Shady Elbassuoni, Carlos Castillo, Fernando Diaz and Patrick Meier. Extracting Information Nuggets from Disaster-Related Messages in Social Media. In Proc. of the 10th International Conference on Information Systems for Crisis Response and Management (ISCRAM), May 2013, Baden-Baden, Germany. (Datasets)

• Muhammad Imran, Shady Elbassuoni, Carlos Castillo, Fernando Diaz and Patrick Meier. Practical Extraction of Disaster-Relevant Information from Social Media. In Social Web for Disaster Management (SWDM'13) - Co-located with WWW, May 2013, Rio de Janeiro, Brazil. (Datasets) | acm)

• Soudip Roy Chowdhury, Muhammad Imran, Muhammad Rizwan Asghar, Sihem Amer-Yahia and Carlos Castillo. Tweet4act: Using Incident-Specific Profiles for Classifying Crisis-Related Messages. In Proc. of the 10th International Conference on Information Systems for Crisis Response and Management (ISCRAM), May 2013, Baden-Baden, Germany.

For a detailed survey on different computational techniques developed to process and analyze social media data, see the following survey paper (accepted in ACM Computing Surveys journal):

Muhammad Imran, Carlos Castillo, Fernando Diaz, Sarah Vieweg: Processing Social Media Messages in Mass Emergency: A Survey. ACM Computing Surveys journal, 2015.