Googling for a concept map: towards automatic concept-map-based query information
David B. Leake, Ana Gabriela Maguitman, Thomas Reichherzer, Alberto J. Cañas, Marco Carvalho, Marco Arguedas, Thomas C. Eskridge · Servicio de Publicaciones eBooks · 2004
Electronic concept mapping tools provide a flexible vehicle for constructing concept maps, linking concept maps to other concept maps and related resources, and distributing concept maps to others. As electronic concept maps are constructed, it is often helpful for users to consult additional resources, in order to jog their memories or to locate resources to link to the map under construction. The World Wide Web provides a rich range of resources for these tasks—if the right resources can be found. This paper presents ongoing research on how to automatically generate Web queries from concept maps under construction, in order to proactively suggest related information to aid concept mapping. First, it examines how concept map structure and content can be exploited to automatically select terms to include in initial queries, based on studies of (1) how concept map structure influences human judgments of concept importance, and (2) the relative value of including information from concept labels and linking phrases. Second, it examines how a concept map can be used to refine future queries by reinforcing the weights of terms that have proven to be good discriminators for the topic of the concept map. The described methods are being applied to developing “intelligent suggesters” to support the concept mapping process.