Educational exploration along the shortest paths in conceptual networks based on co-occurrence, language ability levels and frequency ranking

We propose a new computational method to support learning that relies on adaptive exploration of the shortest paths in conceptual networks that have been formed based on cooccurrences of concepts in suitable text samples and selecting concepts corresponding to desired language ability levels and frequency ranking. Relying on Google Web 1T 5-gram database we have built a conceptual co-occurrence network reaching the coverage of 3018 unique concepts and 54 610 unique pairs of co-occurring concepts thus approximately matching with a vocabulary size suggested to be enough for sufficient comprehension and with the highest language ability levels of English Vocabulary Profile. Our method offers to the learner recommendations about suitable exploration paths along the shortest connecting paths between the concepts belonging to a desired learning topic vocabulary, computed with Yen's algorithm. By indicating for each concept the language ability level and the frequency ranking position in British National Corpus enables to prioritize such shortest paths of concepts that most best match the current suitable comprehension level of the learner. Our preliminary experiment showed that the method can pedagogically intuitively support cumulative adoption of knowledge in the context of study entities belonging to a core curriculum. Relying on our research we are opening a free educational resource at http://www.freelearningpath.org that enables learners and educators to get adaptive guidance for exploring a desired educational content.