Leveraging Cognitive Computing for Multi-class Classification of E-learning Videos

摘要: Multi-class classification aims at assigning each sample to one category chosen among a set of different options. In this paper, we present our work for the development novel system multi-class e-learning videos based on covered educational subjects. The audio transcripts and text depicted into visual frames are extracted analyzed by Cognitive Computing tools, going over traditional term-based similarity approaches. Preliminary experiments demonstrate effectiveness capabilities system, suggesting that semantic analysis improves performance classification.