Association of American Geographers (AAG) Annual Meeting, April 9-13, 2013, Los Angeles.
Paper Session sponsored by the Cartography Specialty Group, the Geographic Information Systems and Science Specialty Group, and the Cyberinfrastructure Specialty Group.
Cyberspace (including web pages, social media, and online communities) is a powerful platform for collective social communications, personal networking, and idea exchanges. Scientists now can trace, monitor, and analyze the spreads of radical social movements, protests, political campaigns, public opinions, etc. via social media and weblogs (Lazer et al. 2009). These research efforts can help us understand the diffusion of innovations (Hägerstrand 1967) and facilitate the discovery of knowledge in cyberspace and social media.Similar to the multidisciplinary research field, called “knowledge discovery in databases (KDD)” (Fayyad et al. 1996), this emerging research field, knowledge discovery in cyberspace (KDC), will focus on how to handle and analyze very large information and human messages collected from cyberspace and social media. The purpose of KDC is to use various tools (machine learning, computational linguistics, GIScience, spatial statistics, geovisualization, etc.) to scale up our research capability of handling millions of records and information items available in social media (such as Twitter) or web pages (searched by Google, Yahoo, or Bing search engines). By developing highly scalable “information mining” algorithms, tools, and methods, scientists and researchers can discover new patterns and new knowledge from very large numbers of message records and human communication networks (social networks).
This paper session aims at formalizing a new research agenda for knowledge discovery in cyberspace (KDC) and exploring possible theories and methods in this new field. This session seeks for papers addressing key questions such as: How to discover meaningful patterns and spatial relationships in social media and web pages? How to avoid the discovery of meaningless patterns or misleading knowledge? How to reduce the huge percentage of “noises” when we collect information from social media and web pages? What kinds of sample sizes or scales are appropriate for various topics and keywords? How to validate these patterns and knowledge found in cyberspace? What types of cartographic or visualization methods can help us discover new patterns? What kinds of space-time analysis methods are needed? Do we need a new conceptual framework for pursuing knowledge discovery in cyberspace and social media?
To present a paper in this session:
- Register and submit your abstract online (http://www.aag.org/cs/annualmeeting).
- Email your presenter identification number (PIN), paper title, and abstract (250 words) to firstname.lastname@example.org (Ming Tsou) by October 19 (Friday), 2012.
- Professor Ming-Hsiang (Ming) Tsou
Department of Geography, San Diego State University, Email: email@example.com ,
NSF-CDI project website: http://mappingideas.sdsu.edu/
- Professor Shaw, Shih-Lung
Department of Geography, University of Tennessee, Knoxville, Email: firstname.lastname@example.org
- Yang, Jiue-An, Department of Geography, San Diego State University. email@example.com
- Han, Su, Department of Geography, San Diego State University. firstname.lastname@example.org
- Fayyad, U., Piatetsky-Shapiro, G., and P. Smyth. (1996). From data mining to knowledge discovery in Databases. AI Magazine, Fall 1996, 17(3), 37–54.
- Hägerstrand, T. (1967) Innovation Diffusion as a Spatial Process. The University of Chicago Press.
- Lazer, D., Pentland, A., Adamic, L., Aral, S., Baraba´si, A. L., Brewer, D., . . . Van Alstyne, M. (2009). Computational social science. Science, 323, 721-723.