Scientific Information Understanding via Open Educational Resources (OER)

摘要: Scientific publication retrieval/recommendation has been investigated in the past decade. However, to best of our knowledge, few efforts have made help junior scholars and graduate students understand consume essence those scientific readings. This paper proposes a novel learning/reading environment, OER-based Collaborative PDF Reader (OCPR), that incorporates innovative scaffolding methods can: 1. auto-characterize student emerging information need while reading paper; 2. enable readily access open educational resources (OER) based on their need. By using metasearch methods, we pre-indexed 1,112,718 OERs, including presentation videos, slides, algorithm source code, or Wikipedia pages, for 41,378 STEM publications. Based computational need, use text mining heterogeneous graph algorithms recommend high quality OERs better content paper. Evaluation results exit surveys an retrieval course show OCPR system alone with recommended can effectively assist complex For instance, 78.42% participants believe provide precise useful they 78.43% them are close exactly what when From OER ranking viewpoint, MRR, MAP NDCG prove learning rank cold start solutions efficiently integrate different features.