Data sets - Humanitarian, Semantics, & Informatics Lab, George Mason University, USA

Datasets for Social, Natural & Humanitarian Crisis Informatics Research

Human_Info_Lab group, George Mason University

(For questions, you can mail Dr. Hemant Purohit: h p u r o h i t at g m u dot e d u)

Natural Crises: Crisis Response Coordination, Intent Mining, Serviceability, Help Seeker-Provider Matching
- H. Purohit, C. Castillo, and R. Pandey. (2020). Ranking and grouping social media requests for emergency services using serviceability model. In Social Network Analysis and Mining (SNAM), 10(1), 1-17. https://doi.org/10.1007/s13278-020-0633-3
  - EVENTS (Twitter): Hurricane Sandy 2012, Oklahoma Tornado 2013, Alberta Floods 2013, Nepal Earthquake 2015, Louisiana Floods 2016, Hurricane Harvey 2017; TYPE: Serviceability (relevance) labels and characteristic ratings for tweets
- J. Krishnan, H. Purohit, and H. Rangwala. (2020). Diversity-Based Generalization for Unsupervised Text Classification under Domain Shift. In Proceedings of the 19th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD).
  - EVENTS (Twitter): Hurricane Harvey 2017, Hurricane Irma 2017, Hurricane Florence 2018; TYPE: relevance labels based on presence of actionable events in tweets
- B. Pedrood, and H. Purohit. (2018). Mining help intent on twitter during disasters via transfer learning with sparse coding. In Proceedings of the 11th Int'l Conference on on Social Computing, Behavioral-Cultural Modeling, & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS).
  - EVENTS (Twitter): Hurricane Sandy 2012, SuperTyphoon Yolanda/Haiyen 2013, Hurricane Harvey 2017, Hurricane Irma 2017; TYPE: help intent labels for tweets
- H. Purohit, and J. Chan. (2017). Classifying User Types on Social Media to inform Who-What-Where Coordination during Crisis Response. In Proceedings of the 14th ISCRAM Conference.
  - EVENTS (Twitter): Louisana Floods 2016, Hurricane Matthew 2016; TYPE: user type labels for Twitter users
- H. Purohit, C. Castillo, F. Diaz, A. Sheth, and P. Meier. (2013). Emergency-relief coordination on social media: Automatically matching resource requests and offers. First Monday, 19(1).
  - EVENTS (Twitter): Hurricane Sandy 2012; TYPE: request-offer intent and resource-type labels for tweets (Courtsey: Kno.e.sis Center)
- H. Purohit, G. Dong, V. Shalin, K. Thirunarayan, and A. Sheth. (2015, December). Intent Classification of Short-Text on Social Media. In 2015 IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity) (pp. 222-228). IEEE.
  - EVENTS (Twitter): Hurricane Sandy 2012, Philippines/Yolanda/Haiyen Typhoon 2013; TYPE: labeled tweets with help intent (Courtsey: Kno.e.sis Center)
- A. Sheth, H. Purohit, A. Smith, J. Brunn, A. Jadhav, P. Kapanipathi, C. Lu, and W. Wang. (2017). Twitris: A system for collective social intelligence. In R. Alhajj & J. Rokne (Eds.), Encyclopedia of social network analysis and mining (pp. 1–23). New York, NY: Springer New York. doi: 10.1007/978-1-4614-7163-9_345-1.
  - EVENTS (Twitter): Hurricane Sandy 2012, Queensland Floods 2013, Boston Bombing 2013, Oklahoma Tornado 2013, Alberta Floods 2013, Philippines/Yolanda/Haiyen Typhoon 2013; TYPE: public tweets during disasters (Courtsey: Kno.e.sis Center)
Societal Crises and activism: Gender-based Violence and User Attitudes
- R. Pandey, H. Purohit, B. Stabile, and A. Grant. (2018). Distributional Semantics Approach to Detect Intent in Twitter Conversations on Sexual Assaults. In Proceedings of the 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI).
  - Tweets containing gender-based violence related keywords, shared in Fall 2016; TYPE: malicious intent labels for tweets
- P. Karuna, H. Purohit, B. Stabile, and A. Hattery. (2017). On User Engagement across Social Media Campaigns to Curb Gender-based Violence. The 10th International Conference on on Social Computing, Behavioral-Cultural Modeling, & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS), 2017.
  - EVENTS (Twitter): StateOfWomen, ItsOnUs, HeForShe campaigns in 2016; TYPE: tweets associated with hashtag campaigns related to gender-based violence
- H. Purohit, T. Banerjee, A. Hampton, V. Shalin, N. Bhandutia, and A. Sheth. (2016). Gender-based violence in 140 characters or fewer: A #BigData case study of Twitter. First Monday, 21(1).
  - Gender violence related worldwide Twitter data; TYPE: public tweets related to gender-based violence (Courtsey: Kno.e.sis Center)
- Y. Ruan, H. Purohit, D. Fuhry, S. Parthasarathy, and A. Sheth. (2012). Prediction of Topic Volume on Twitter. In International ACM Conference on Web Science (Vol. 397, p. 402).
  - EVENTS (Twitter): India Against Corruption movement, Occupy Wall Street movement, Penn State Coach Scandal, 2011; TYPE: public tweets generated during specific societal events (Courtsey: Kno.e.sis Center)