SensePlace3 – Analyzing place–time–attribute information in big social media data


SensePlace2 / SensePlace3 was a project we collaborated on with research groups at The Pennsylvania State University in the Geography DepartmentCollege of Information Sciences and Technology, and Computer Science and Engineering Department. This project was funded by the US Department of Homeland Security (DHS) and the US Army Engineer Research and Development Center (ERDC), Geospatial Research Laboratory. Our goal was to analyze place-time-attribute information found in Twitter tweets and make sense of places from millions of tweets. Not only did we build a system to map and analyze the small percentage of tweets where the user enabled their location, but we also led the way to analyze the places mentioned in the tweets. Our work was one of the first to describe using tweets and their location data for situational awareness during emergencies. It also led to important discussions in the research and emergency response communities of the ethics of location-based data in crisis situations. The videos below highlight the system, the problem it addresses, and its goals.

Video 1: SensePlace2: Visual Analytics and Big Data for Spatiotemporal Sensemaking

Video 2: SensePlace2 Functionality – October 2012

Video 3: SensePlace2 – Geo Twitter Analytics


SensePlace2/SensePlace3 was recently selected for the Institute of Electrical and Electronics Engineers (IEEE) Visual Analytics Science and Technology (VAST) Test of Time Award presented at the 2021 IEEE VIS Conference. Specifically, our article SensePlace2: GeoTwitter analytics support for situational awareness from 2011 was awarded. Our collaborator, Dr. Anthony Robinson, gave the acceptance speech below.


Video 4: IEEE VAST 2021 Test of Time Award acceptance speech.

The award committee members – Brian Fisher, Shixia Liu, Catherine Plaisant (chair), Jonathan Roberts – chose our article because: The paper has over 400 citations, and is still regularly cited today as an early example of visual analytics for aggregated social media data. Published when Twitter was still ramping up, the paper described using tweets and their location data for situation awareness during emergencies. It includes a survey of emergency practitioners and a useful discussion of situation awareness. This work led to important discussions of the ethics of location-based data in crisis situations. SensePlace2/SensePlace3 produced many other academic research publications. The publications that we contributed to are listed below.


We were fortunate to collaborate from the beginning of this project. We:

  1. Met with key DHS and US Army Corps of Engineers to understand their problem.
  2. Contributed to novel research ideas to solve the challenge of making sense from big social media data.
  3. Implemented technical solutions involving:
    1. Natural language processing to extract place, people, and organizations text.
    2. Information Retrieval and search engine technology to return most relevant tweets to the user searches.
    3. Geographic Information Retrieval to parse and geocode place mentions
    4. Full stack geovisual web application development involving Postgresql/PostGIS, Java web services, and many JavaScript mapping, visualization, and Web 2.0 client APIs to create a human-in-the-loop geovisual analytics system.
    5. Devised many strategies to handle, process, search, and display nearly 30 million tweets per month in near real-time.
  4. Presented at international academic conferences and many times to top project officials at the funding agencies.
  5. Wrote academic articles for top international publication outlets.

The following GeoVISTA Center article describes our work with the Institute for Computational and Data Sciences (ICDS) to overcome the technical challenges of dealing with this messy big data source.


Posed with the problem of making sense from place-time-attribute information in big social media data, we helped create a geovisual analytics system to allow a human-in-the-loop sense-making process. This project also spun off GeoTxt, a web API for geoparsing and geocoding of place names in text documents, that we contributed heavily towards.

Leave a Reply

Your email address will not be published. Required fields are marked *