CI-KNOW: Recommendation based on social networks

Yun Huang, Noshir Contractor, York Yao

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Recent advances in Web 2.0 and cyberinfrastructure have enabled new levels of interactions and interconnections among individuals, documents, data, analytic tools and concepts. For communities to be more effective in using these resources, it is even more crucial that they have tools help them identify the right expertise or knowledge resources from within this large "multidimensional network." Cyberinfrastructure Knowledge Networks on the Web (CI-KNOW) is a suite of Web-based tools that facilitates discovery of resources within communities. CKNOW facilitates discovery by implementing a network recommendation system that incorporates social motivations for why we create, maintain, and dissolve our knowledge network ties. The network data is captured by automated harvesting of digital resources using Web crawlers, text miners, tagging tools that automatically generate community-oriented metadata, and scientometric data such as co-authorship and citations. Based on this knowledge network, the CI-KNOW recommender system produces personalized search results through two steps: identify matching entities according to their metadata and network statistics and select the best fits according to requester's perspectives and connections in the social network. Integrated with community Web portals, CI-KNOW navigation and auditing portlets provide analysis and visualization tools for community members and serves as a research testbed to test social networks models about individuals' motivations for seeking expertise from specific resources (people documents, datasets, etc.). As a proof-of-concept, this paper demonstrates how CI-KNOW has been integrated with the NCI-supported Tobacco Informatics Grid (TobIG) to facilitate knowledge sharing in the tobacco control research community.
Original languageEnglish (US)
Title of host publicationdg.o '08 Proceedings of the 2008 International Conference on Digital Government Research
EditorsSoon A Chun, Marijn Jansen, Jose R Gil-Garcia
PublisherDigital Government Society of North America
Number of pages2
ISBN (Print)978-1605580999
StatePublished - 2008

Publication series

NameACM International Conference Proceeding Series

Fingerprint Dive into the research topics of 'CI-KNOW: Recommendation based on social networks'. Together they form a unique fingerprint.

Cite this