2016 Workshop 5 – Analyzing Social Media Data from a Spatiotemporal Perspective: Using Geocoding Tools and Space-Time Analysis Methods
Abstract: Spatiotemporal analysis is essential for social media analytic applications, such as disease outbreak monitoring, marketing analysis, and business analytics. To understand the spatial and temporal distribution patterns of social media messages, researchers need to use geocode engines and space-time analysis methods to enhance their research models and analytic frameworks. This workshop will provide a good overview of geocoding methods for Twitter data by Dr. Ming-Hsiang Tsou and space-time analysis methods by Dr. Tao Cheng and Juntao Lai.
The geocoding method section will include various mapping approaches using geo-tagged tweets, user profile locations, place name extraction from texts, and the analysis of historical locations of individual users. We will also introduce several geocoding engines, including Google Map Geocoding API, Yahoo BOSS PlaceFinder, and OpenStreetMap Nominatim. Popular digital gazetters, such as GeoNames.org and the gazetteer of the Library of Congress (http://loc.gazetteer.us/) will also be discussed.
The section in space-time analysis methods will demonstrate how user interests and place profiles can be inferred from text harvested from geo-tagged Tweets. We will introduce an unsupervised topic modelling method, Latent Dirichlet Allocation (LDA) to extract meaningful topics from Tweets, and the clustering methods to generate the profile of places based upon the space-time patterns of these topics.
- Participants should bring their own laptop computers and power cords for conducting web- based tutorials.
- Participants will need to access their own Twitter accounts and install R (preferable R studio) in their computers.
Ming-Hsiang Tsou – firstname.lastname@example.org
Dr. Ming-Hsiang (Ming) Tsou is a Professor in the Department of Geography, San Diego State University (SDSU) and the Director of the Center for Human Dynamics in the Mobile Age (HDMA). His research interests are in Human Dynamics, Social Media, Big Data, Visualization, and Internet GIS. He served on the editorial boards of the Annals of GIS (2008-), Cartography and GIScience (2013-) and the Professional Geographers (2011-) and two U.S. National Academy of Science Committees. In 2010, Tsou was awarded to a $1.3 million research grant funded by National Science Foundation and served as the Principal Investigator (PI) of, “Mapping ideas from Cyberspace to Realspace” (http://mappingideas.sdsu.edu/) research project (2010-2014). This NSF-CDI project integrates GIS, computational linguistics, web search engines, and social media APIs to track and analyze public-accessible websites and tweets for analyzing the diffusion of information in cyberspace. In Spring 2014, Tsou established a new research center, Human Dynamics in the Mobile Age (http://humandynamics.sdsu.edu/), a transdisciplinary research area of excellence at San Diego State University to integrate research works from GIScience, Public Health, Social Science, Sociology, and Communication. In Fall 2014, Tsou received a NSF Interdisciplinary Behavioral and Social Science Research (IBSS) award, “Spatiotemporal Modeling of Human Dynamics Across Social Media and Social Networks” ($999,887, 2014-2018, http://socialmedia.sdsu.edu ). This large interdisciplinary research project studies human dynamics across social media and social networks, focusing on information diffusion and the connection between online activities and real world human behaviors.
Dr. Tao Cheng is a Professor in GeoInformatics and the Director of SpaceTime Lab (www.ucl.ac.uk/spacetimelab) at the University College London (UCL), a multi-disciplinary research centre that aims to gain insight from geo-located and time-stamped data in order to improve urban living. Her research interests span network complexity, Geocomputation, integrated spatio-temporal analytics (modelling, prediction, clustering, visualisation and simulation) and Big data mining with applications in transport, crime, health, social media, and natural hazards. She has worked with private and public partners including Transport for London (TfL), the London Metropolitan Police and Arup. She led the STANDARD project; the first attempt to mine transport network data in order to understand congestion in Central London (EPSRC, £794,570). She is currently leading the CPC project (Crime, Policing and Citizenship – Space-Time Interaction of Dynamic Networks, EPSRC, £1.4M); part of the Global Uncertainties Programme; which aims to understand and predict when, where and how criminal activities emerge and are sustained (www.ucl.ac.uk/cpc). She is the Co-I of the Consumer Data Research Centre (http://cdrc.ac.uk), the largest project funded by UK ESRC Big Data initiatives (£6.1M), a national platform and service that will unlock the potential of ‘Big’ retail data for research and public service.
Juntao Lai is a Ph.D. student at SpaceTimeLab. He did his undergraduate study in Remote Sensing at Wuhan University, China. He joined the lab after finished his MSc of Geospatial Analysis at UCL Geography in October 2014. His research interests include social media data analytics, sentiment analysis and spatial temporal data mining. He is currently studying the influences of social media on the public satisfaction towards police.