Mining social media to inform peatland fire and haze disaster management

  • Mark Kibanov
  • Gerd Stumme
  • Imaduddin Amin
  • Jong Gun Lee
Original Article


Peatland fires and haze events are disasters with national, regional, and international implications. The phenomena lead to direct damage to local assets, as well as broader economic and environmental losses. Satellite imagery is still the main and often the only available source of information for disaster management. In this article, we test the potential of social media to assist disaster management. To this end, we compare insights from two datasets: fire hotspots detected via NASA satellite imagery and almost all GPS-stamped tweets from Sumatra Island, Indonesia, posted during 2014. Sumatra Island is chosen as it regularly experiences a significant number of haze events, which affect citizens in Indonesia as well as in nearby countries including Malaysia and Singapore. We analyze temporal correlations between the datasets and their geo-spatial interdependence. Furthermore, we show how Twitter data reveal changes in users’ behavior during severe haze events. Overall, we demonstrate that social media are a valuable source of complementary and supplementary information for haze disaster management. Based on our methodology and findings, an analytics tool to improve peatland fire and haze disaster management by the Indonesian authorities is under development.



We thank Johan Kieft from UN Environment who provided insight about haze disasters in Indonesia and George Hodge from Pulse Lab Jakarta for his assistance. Furthermore, we acknowledge the use of FIRMS data and imagery from the Land, Atmosphere Near real-time Capability for EOS (LANCE) system operated by the NASA/GSFC/Earth Science Data and Information System (ESDIS) with funding provided by NASA/HQ.


  1. Abel F, Hauff C, Houben G-J, Stronkman R, Tao K (2012) Semantics + filtering + search = twitcident. Exploring information in social web streams. In: Proceedings of the 23rd ACM conference on hypertext and social media, HT ’12. ACM, New York, pp 285–294Google Scholar
  2. Amin S, Goldstein M (2008) Data against natural disasters: establishing effective systems for relief, recovery, and reconstruction. The World Bank, WashingtonCrossRefGoogle Scholar
  3. Avvenuti M, Cresci S, Marchetti A, Meletti C, Tesconi M (2014a) EARS (earthquake alert and report system): a real time decision support system for earthquake crisis management. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’14. ACM, New York, pp 1749–1758Google Scholar
  4. Avvenuti M, Cresci S, Polla MNL, Marchetti A, Tesconi M (2014b) Earthquake emergency management by social sensing. In: 2014 IEEE international conference on pervasive computing and communications workshops (PERCOM Workshops), pp 587–592Google Scholar
  5. Cameron MA, Power R, Robinson B, Yin J (2012) Emergency situation awareness from Twitter for crisis management. In: Proceedings of the 21st international conference on World Wide Web, WWW ’12 Companion. ACM, New York, pp 695–698Google Scholar
  6. Carley KM, Malik M, Kowalchuk M, Pfeffer J, Landwehr P (2015) Twitter usage in Indonesia. Technical report, Institute for Software Research, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213Google Scholar
  7. Cresci S, Cimino A, DellOrletta F, Tesconi M (2015) Crisis mapping during natural disasters via text analysis of social media messages. In: Wang J, Cellary W, Wang D, Wang H, Chen S-C, Li T, Zhang Y (eds) Web information systems engineering WISE 2015. Lecture notes in computer science, vol 9419. Springer International Publishing, New York, pp 250–258. doi: 10.1007/978-3-319-26187-4_21 CrossRefGoogle Scholar
  8. Feasibility study: supporting forest and peat fire management using social media. Technical report 10, UN Global Pulse (2014)Google Scholar
  9. Frankenberg E, McKee D, Thomas D (2005) Health consequences of forest fires in Indonesia. Demography 42(1):109–129CrossRefGoogle Scholar
  10. Gao H, Barbier G, Goolsby R (2011) Harnessing the crowdsourcing power of social media for disaster relief. IEEE Intell Syst 26(3):10–14CrossRefGoogle Scholar
  11. Goolsby R (2010) Social media as crisis platform: the future of community maps/crisis maps. ACM Trans Intell Syst Technol 1(1):7:1–7:11CrossRefGoogle Scholar
  12. Holmgren P (2015) Fire and haze in Riau: looking beyond the hotspots. Retrieved 15 Sept.
  13. Impact of Haze on Health, Singapore Government, Health Promotion Board. Retrieved 15 Sept 2015.
  14. Indonesia: number of Twitter users 2014–2019, emarketer. Retrieved 30 Jan.
  15. Iliadis LS (2005) A decision support system applying an integrated fuzzy model for long-term forest fire risk estimation. Environ Model Softw 20(5):613–621CrossRefGoogle Scholar
  16. Imran M, Castillo C, Diaz F, Vieweg S (2015) Processing social media messages in mass emergency: a survey. ACM Comput Surv 47(4):67:1–67:38CrossRefGoogle Scholar
  17. Imran M, Castillo C, Lucas J, Meier P, Vieweg S (2014) AIDR: artificial intelligence for disaster response. In: Proceedings of the 23rd international conference on World Wide Web, WWW ’14 Companion, Republic and Canton of Geneva, Switzerland, pp 159–162. International World Wide Web Conferences Steering CommitteeGoogle Scholar
  18. Imran M, Elbassuoni S, Castillo C, Daz F, Meier P (2013) Extracting information nuggets from disaster-related messages in social media. In: Comes FFT (ed) Proceedings of 10th international conference on information systems for crisis response and management, ISCRAM 2013. Karlsruher Institut fur Technologie, KIT, Baden-Baden, pp 791–801Google Scholar
  19. Jaiswal RK, Mukherjee S, Raju KD, Saxena R (2002) Forest fire risk zone mapping from satellite imagery and GIS. Int J Appl Earth Obs Geoinf 4(1):1–10CrossRefGoogle Scholar
  20. Karhutla riau - ini pembakaran bukan kebakaran. Gema BNPB Ketangguhan Bangsa Dalam Menghadapi Bencana, 5 (May 2014)Google Scholar
  21. Kim D-H, Sexton JO, Townshend JR (2015) Accelerated deforestation in the humid tropics from the 1990s to the 2000s. Geophys Res Lett 42(9):3495–3501CrossRefGoogle Scholar
  22. Krstajić M, Rohrdantz C, Hund M, Weiler A (2012) Getting there first: real-time detection of real-world incidents on Twitter. In: The 2nd workshop on interactive visual text analytics: task-driven analysis of social media contentGoogle Scholar
  23. Kryvasheyeu Y, Chen H, Obradovich N, Moro E, Van Hentenryck P, Fowler J, Cebrian M (2016) Rapid assessment of disaster damage using social media activity. Sci Adv 2(3):e1500779–e1500779CrossRefGoogle Scholar
  24. Kumar S, Barbier G, Abbasi MA, Liu H (2011) TweetTracker: an analysis tool for humanitarian and disaster relief. In: Proceedings of the fifth international AAAI conference on weblogs and social media, ICWSM ’11. AAAI Press, Menlo ParkGoogle Scholar
  25. Mandel B, Culotta A, Boulahanis J, Stark D, Lewis B, Rodrigue J (2012) A demographic analysis of online sentiment during hurricane irene. In: Proceedings of the second workshop on language in social media, LSM ’12. Association for Computational Linguistics, Stroudsburg, pp 27–36Google Scholar
  26. Middleton SE, Middleton L, Modafferi S (2014) Real-time crisis mapping of natural disasters using social media. IEEE Intell Syst 29(2):9–17CrossRefGoogle Scholar
  27. Morstatter F, Lubold N, Pon-Barry H, Pfeffer J, Liu H (2014) Finding eyewitness tweets during crises. In: Proceedings of the ACL 2014 workshop on language technologies and computational social science, pp 23–27. Association for Computational Linguistics, BaltimoreGoogle Scholar
  28. NASA Active Fires, NASA FIRMS. Retrieved 20 Aug 2015.
  29. NASA Fire Information for Resource Management System (FIRMS). Retrieved 20 Aug 2015.
  30. Oz T, Bisgin H (2016) Attribution of responsibility and blame regarding a man-made disaster: #FlintWaterCrisis. In: Workshop social web for disaster management, Indianapolis, USAGoogle Scholar
  31. Prasetyo PK, Gao M, Lim E-P, Scollon CN (2013) Social sensing for urban crisis management: the case of Singapore haze. In: Social informatics. Lecture notes in computer science, vol 8238. Springer International Publishing, New York, pp 478–491Google Scholar
  32. Rogstadius J (2014) Enhancing disaster situational awareness through scalable curation of social media. PhD thesis, Universidade da Madeira, MadeiraGoogle Scholar
  33. Rogstadius J, Vukovic M, Teixeira C, Kostakos V, Karapanos E, Laredo J (2013) CrisisTracker: crowdsourced social media curation for disaster awareness. IBM J Res Dev 57(5):4:1–4:13CrossRefGoogle Scholar
  34. Sakaki T, Okazaki M, Matsuo Y (2010) Earthquake shakes Twitter users: real-time event detection by social sensors. In: Proceedings of the 19th international conference on World Wide Web, WWW ’10. International World Wide Web Conferences Steering Committee, New York, pp 851–860Google Scholar
  35. Sakr G, Elhajj I, Mitri G, Wejinya U (2010) Artificial intelligence for forest fire prediction. In: 2010 IEEE/ASME international conference on advanced intelligent mechatronics, AIM ’10. Institute of Electrical & Electronics Engineers (IEEE)Google Scholar
  36. Schulz A, Ristoski P, Paulheim H (2013) I see a car crash: real-time detection of small scale incidents in microblogs. In: The semantic web: ESWC 2013 satellite events. Lecture notes in computer science, vol 7955. Springer, Berlin, pp 22–33Google Scholar
  37. Sitanggang IS, Ismail MH (2011) Classification model for hotspot occurrences using a decision tree method. Geomat Nat Hazards Risk 2(2):111–121CrossRefGoogle Scholar
  38. Zhang S, Vucetic S (2016) Semi-supervised discovery of informative tweets during the emerging disasters. In: Workshop social web for disaster management, Indianapolis, USAGoogle Scholar

Copyright information

© Springer-Verlag GmbH Austria 2017

Authors and Affiliations

  • Mark Kibanov
    • 1
  • Gerd Stumme
    • 1
  • Imaduddin Amin
    • 2
  • Jong Gun Lee
    • 2
  1. 1.Knowledge and Data Engineering Group, ITeG Research CenterUniversity of KasselKasselGermany
  2. 2.Pulse Lab JakartaUN Global Pulse, United NationsJakartaIndonesia

Personalised recommendations