Social Web has moved knowledge production from the hands of the experts and professionals to the masses. Today online social networking sites, such as Twitter, Facebook, YouTube, and Flickr, allow ordinary people not only to create massive quantities of new data, but also organize it, use it, and share it with others. Unlike earlier information technologies, the Social Web exposes social activity, allowing each person to observe and be influenced by the actions of others in real time. How will such real-time, many-to-many communication change how we discover, use, and manage information? And how will it transform society and how we solve problems? My research addresses these questions by developing methods to harvest social knowledge. Consider a gazetteer, for example, Geonames.org, which compiles geospatial knowledge within a directory of places and place names, often organizing it hierarchically within taxonomy of geospatial concepts. Such gazetteers have been useful for creating geo-aware applications and integrating geospatial knowledge. However, since gazetteers are manually and painstakingly created by an expert or a small group of experts, they are rarely complete or comprehensive, do not reflect the variety of views, and fail to keep up with our changing ideas about places.
[1]
Kristina Lerman,et al.
Constructing folksonomies from user-specified relations on flickr
,
2009,
WWW '09.
[2]
Kristina Lerman,et al.
Harvesting geospatial knowledge from social metadata
,
2010,
ISCRAM.
[3]
Kristina Lerman,et al.
Integrating Structured Metadata with Relational Affinity Propagation
,
2010,
Statistical Relational Artificial Intelligence.
[4]
Kristina Lerman,et al.
Modeling Social Annotation: A Bayesian Approach
,
2008,
TKDD.
[5]
Kristina Lerman,et al.
Automatically Constructing Semantic Web Services from Online Sources
,
2009,
SEMWEB.
[6]
Kristina Lerman,et al.
Growing a tree in the forest: constructing folksonomies by integrating structured metadata
,
2010,
KDD.
[7]
Kristina Lerman,et al.
Exploiting Social Annotation for Automatic Resource Discovery
,
2007,
ArXiv.