I-Corps: Fragmented Learning App based on Knowledge Graphs

Award ID: 2034508

The broader impact/commercial potential of this I-Corps project is the development of a Fragmented Learning App based on knowledge graphs to improve the effectiveness and efficiency of fragmented learning as a complement to the traditional collective learning in the classroom setting. This goal is to examine the impact of the fragmented learning style on various types of domain knowledge versus the (predominantly used) collective learning style. The proposed technology will explore how knowledge graphs may represent and organize knowledge (e.g., concepts, theorems, principles, rules) in various domains and enable knowledge reasoning and derivation. Data from various types of users will be collected to enrich and evolve the knowledge graphs based on the latest learning needs. This I-Corps project is based on the development of technology to support fragmented learning, which allows users to study anytime and anywhere as well as on various platform, improving their learning effectiveness and efficiency. Specially, the proposed technology is designed by integrating knowledge graphs with machine/deep learning and Natural Language Processing models to recommend relevant learning materials based on coherent and evolving knowledge graphs rather than user-constructed keyword search. The app constructs both a complete knowledge graph for a knowledge domain and a personalized knowledge graph for the individual user to generate a personalized learning plan adapted to his/her individual learning needs. Leveraging knowledge graphs to represent and organize knowledge from big data sources (text and video tutorials), the Fragmented Learning App captures explicit and implicit relations of knowledge and derives new knowledge and relations to prevent fragmenting the domain knowledge. In addition, the technology incorporates the social platform and observer roles for user interaction and knowledge exchange. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Ruth Shuman