Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Twitris in Action - a review of its many applications

64 views

Published on

Twitris is a System for Collective Social Intelligence. It has been used in a large number of and many types (disaster coordination, banding, epidemiology, public health, election/polical, social movement) of applications - often in real-time. This presentation gives a bird-eye review of some of these applications with links to explore them further.

Published in: Social Media
  • Be the first to comment

  • Be the first to like this

Twitris in Action - a review of its many applications

  1. 1. Applications of Twitris Technology: Real-time, Actionable Insights from Social Media Rotary Meeting, Fairborn, Ohio.16th May 2018 Prof. Amit Sheth LexisNexis Ohio Eminent Scholar Exec. Dir. - Kno.e.sis @ Wright State University
  2. 2. Data used for this simulation was based on repurposing of 2013 Boston Bombing dataset. More: Hampton et al. Constructing Synthetic Social Media Stimuli for an Emergency Preparedness Functional Exercise. ISCRAM-2017. Designing Real-time Coordination Tools: Dayton Regional EM Exercise 2 Snapshot Twitris-based simulation tool for filtering social system Used in a functional exercise of emergency response organizations City: Dayton Date: 5/28/14
  3. 3. https://upload.wikimedia.org/wikipedia/commons/7/7c/Conversationprism.jpeg Never before humanity is so connected IEEE Internet Computing, 2009 3
  4. 4. https://www.flickr.com/photos/25031050@N06/3292307605 ICWSM-13 Tutorial: Crisis Mapping & Citizen Sensing 4
  5. 5. The Origin The idea for Twitris came on 26 Nov 2008 when terrorist stuck at 9 locations in Mumbai for 3 days. It was clear that social media had become a preferred way for sharing breaking news and real-time news dissemination, but it was hard to achieve situal awareness from the torrent of social media posts. 5
  6. 6. Social Data is incredibly rich. Real-time analysis of v1: Spatio-Temporal-Thematic v2: People-Content-Network v3: Sentiment-Emotion-Intention v4: Semantic filtering/knowledge graph, IFTTT, scalability, robustness Commercial: Cognovi Labs TWITRIS’ technical Approach to Understand & Analyze Social Content 6
  7. 7. 7 Twitris Technology: Real-time, Actionable Insights from Social-media S-E-I Sentiment-Emotion-Intent Extracts and assigns structured sentiment and emotion scoring from unstructured content to understand motivation, feelings, opinion and intent. S-T-T Spatio-Temporal-Thematic Provides thematic context through analysis of place and time. P-C-N People-Content-Network Analyzes influential users and identifies who is being listened to. Key Differentiators: ● Comprehensive (above) ● Semantic Processing: use of public and proprietary knowledge. ● Real-time processing: used in live blogging of election debate; coordination during disasters. ● Scalable: deployed on a large cloud (864 CPUs, 17 TB main, 435 TB disk).
  8. 8. Snapshot of Some Real-world Applications/Trials 8
  9. 9. Snapshot of Some Real-world Applications/Trials Domains: Branding, Disaster Coordination, Social Movements, Election, Development, Epidemiology, etc. 9
  10. 10. • Coordination during disasters (QCRI, Microsoft Research NYC, CrisisNET, UN) • Harassment on social media (WSU cognitive scientists) • Prescription drug and opioid abuse, Cannabis & Synthetic Cannabinoid epidemiology (Center for Interventions, Treatment and Addictions Research, ….) • Depressive disorders (Weill Cornell Med) • Gender-based violence (UNFPA), Zika Spread • and extensive applications in personalized digital health, public health (Dayton Children’s Hospital, Wright St Physicians, …) Highly multidisciplinary team efforts, often with significant partners, with real world data, intended to achieve real-world impact Some of the significant human, social & economic development applications we work on at Kno.e.sis 10
  11. 11. 11 Public Interest: US Healthcare Reform Debate - 2009 More: https://www.youtube.com/watch?v=OHuFtHXlhtw
  12. 12. 12 Election Prediction: US Election - Nov., 2012 More: http://twitris.knoesis.org/insights/Election2012 http://www.dataversity.net/election-2012-the-semantic-recap/
  13. 13. Disaster Relief: Sample of Real-World Impact & Media Coverage Oct 12, 2013 Google's Person Finder and Google Crisis Response Map for Phailin to help with crisis information Jun 27, 2013 Using crisis mapping to aid Uttarakhand Jun 24, 2013 Twitris: Taking Crisis Mapping to the Next Level Sep 11, 2012 Could Twitris+ Be Used for Disaster Response? Dec 7, 2015 Chennai floods: How social media and crowdsourcing helps people on ground Sep 9, 2014 Digital soldiers emerge heroes in Kashmir flood rescue And many other topics: Emoji, Religion, Gun Violence, Public Policy, Smart City, Health, Election (currently predicting: Election2012, Brexit, Election2016, ALSenate): http://knoesis.org/amit/media/
  14. 14. Example of coordination during #Oklahoma-tornado response based on automatically matching need-offer pairs of community members. More: Purohit et al. Emergency-relief coordination on social media: Automatically matching resource requests and offers. First Monday, 14 Disaster Relief: Oklahoma Tornado - May, 2013
  15. 15. Google Crisis Map for Hurricane Phalin, which used data from international participants spearheaded by Twitris team at the Kno.e.sis center. More on - https://goo.gl/iB2LHg 15 Disaster Relief: Hurricane Phalin - Oct., 2013
  16. 16. More: Purohit et al. Empowering Crisis Response-Led Citizen Communities: Lessons Learned from JKFloodRelief.org Initiative. IGI Global book, 2016. Rescue and Evacuation Stream Map during the historic Jammu & Kashmir Floods in Sep/2014. Twitris supported the scalable relief effort of JKFloodRelief.org initiative. 16 Disaster Relief: Kashmir Floods - Sep., 2014
  17. 17. Moriam Nessa Sep 8th, 11:09am I do not know if anyone will be reading this message and if this will be of any help. But I have my sister who is stranded in Srinagar. She is 9 months pregnant and they need help. We have been trying to get through the help lines but nothing is working. Somebody please help ... ADGPI - Indian Army Sep 8th, 3:24pm Jawahar Nagar is heavily flooded. Rescue teams will be going there. So don't worry they will be alright. Indian Army is there Moriam Nessa Sep 8th, 7:28pm Hey, Thank you so much for your effort in rescue operations. But I’m writing to you again about update of the situation in Jawahar Nagar. My concern is that a young girl there is pregnant. Moriam Nessa Sep 9th, 8:27am Thank you so much again for your relief work. My sister has been rescued. All thanks to you and your team. 17More: https://www.hindustantimes.com/india/digital-soldiers-emerge-heroes-in-kashmir-flood-rescue/story-WuHYPkoQxNtJQzvVMLDnqK.html Disaster Relief: Kashmir Floods - Sep., 2014
  18. 18. 18 Other: U.S. Religious Landscape - Oct., 2014 More: https://www.technologyreview.com/s/531446/twitter-data-mining-reveals-americas-religious-fault-lines/ Lu Chen et al., U.S. Religious Landscape on Twitter. Social Informatics (SocInfo), 2014.
  19. 19. 19 Other: City Traffic Event Identification - Jul., 2015 More: Pramod Anantharam et al.,. 2015. Extracting City Traffic Events from Social Streams. ACM Trans. Intell. Syst. Technol. 6, 4, Article 43 (July 2015)
  20. 20. 20 Social Good: Combating Cyberbullying - Sep., 2015 More: https://youtu.be/gL1e0dQre_0 http://wiki.knoesis.org/index.php/Context-Aware_Harassment_Detection_on_Social_Media
  21. 21. Twitris Chennai Flood Map 21More: https://www.oneindia.com/india/chennai-floods-rescue-operations-social-media-technology-twitter-1947228.html Disaster Relief: Chennai Floods - Dec., 2015
  22. 22. 22 Social Good: Gender-based Violence - Jan., 2016 More: Hemant Purohit et al., Gender-Based Violence in 140 Characters or Fewer: A #BigData Case Study of Twitter, First Monday, 2016.
  23. 23. 23 Public Referendum: Brexit - Jun., 2016 More: https://techcrunch.com/2016/06/29/the-twitris-sentiment-analysis-tool-by-cognovi-labs-predicted-the-brexit-hours-earlier-than-polls/
  24. 24. 24 Election Prediction: US Election - Nov., 2016 More: https://www.whio.com/news/local/wsu-researchers-monitored-twitter-predict-trump-victory/pdPJiwLFxNKCH5J7zER9BJ/ https://www.linkedin.com/pulse/election-day-socialmedia-analysis-election2016-06nov2016-amit-sheth/
  25. 25. 25 Social Good: Street Gang Member Profile Identification - Nov., 2016 More: http://webapp2.wright.edu/web1/newsroom/2018/03/06/gang-guidance/ Lakshika Balasuriya et al., Finding Street Gang Members on Twitter. IEEE/ACM ASONAM, 2016
  26. 26. 26 Health: Understanding Edible Marijuana Use in the USA - Apr., 2017 More: http://www.daytoncitypaper.com/eat-it-then-tweet-it/ Lamy, Francois R. et al., “Those edibles hit hard”: Exploration of Twitter data on cannabis edibles in the U.S, Drug & Alcohol Dependence , Volume 164 , 64 - 70
  27. 27. 27 Health: Combatting Depression - Jul., 2017 More: http://wiki.knoesis.org/index.php/Modeling_Social_Behavior_for_Healthcare_Utilization_in_Depression Amir Yazdavar et al., Semi-Supervised Approach to Monitoring Clinical Depressive Symptoms in Social Media. IEEE/ACM ASONAM, 2017
  28. 28. 28 Election Prediction: Alabama Senate - Dec., 2017 More: http://www.centerforpolitics.org/crystalball/articles/can-twitter-predict-elections/ https://www.linkedin.com/pulse/hat-trick-aka-triple-play-going-against-tide-calling-election-sheth/
  29. 29. 29 Other: Emoji Understanding - Jan., 2018 More: Sanjaya Wijeratne et al., EmojiNet: An Open Service and API for Emoji Sense Discovery. ICWSM 2017. Montreal, Canada; 2017. http://emojinet.knoesis.org/home.php
  30. 30. 30
  31. 31. More details treatment of some of the technical topics • http://wiki.knoesis.org/index.php/Twitris, http://twitris.knoesis.org • WWW2011: “Citizen Sensor Data Mining, Social Media Analytics and Development Centric Web Applications,” with Meena Nagarajan and Selvam Velmurugan. • ICWSM2013:”Crisis Mapping, Citizen Sensing and Social Media Analytics: Leveraging Citizen Roles for Crisis Response,” with Carlos Castillo, Patrick Meier, and Hemant Purohit. Media stories: http://knoesis.org/amit/media Twitris and/or Semantic Social Web Research @ Kno.e.sis: : K. Gomadam, M. Nagarajan, A. Ranabahu, H. Purohit, W. Wang, L. Chen, P. Anantharam, A. Jadhav, P. Kapanipathi, Alan Gary Smith, Jeremy Brunn, Mike Partin, Dr. T.K. Prasad, Dr. Valerie Shalin and many others Funding: NSF, AFRL, NIH; Collaborations: IBM, Microsoft Special thanks (preparing this presentation): Sanjaya Wijeratne Acknowledgements 31
  32. 32. Thank You!

×