Abstract:
We propose a new method for guided generation of concept maps from open accessonline knowledge resources such as Wikies. Based on this method we have implemented aprototype extracting semantic relations from sentences surrounding hyperlinks in the Wikipedia’sarticles and letting a learner to create customized learning objects in real-time based oncollaborative recommendations considering her earlier knowledge. Open source modules enablepedagogically motivated exploration in Wiki spaces, corresponding to an intelligent tutoringsystem. The method extracted compact noun–verb–noun phrases, suggested for labeling arcsbetween nodes that were labeled with article titles. On average, 80 percent of these phrases wereuseful while their length was only 20 percent of the length of the original sentences. Experimentsindicate that even simple analysis algorithms can well support user-initiated information retrievaland building intuitive learning objects that follow the learner’s needs.