Today's concept of the day is the latent Dirichlet allocation (LDA), which is the method used in this paper (18 page PDF) to analyze 41,925 journal articles published between 2000 and 2019. Basically the method uses an algorithm to group clusters of word stems into underlying topics. The study identified 16 topics reflecting "emerging trends and developments". Based on this, the authors say, "the next decade of e-learning studies will focus on learning factors and algorithms, which will possibly create a baseline for more individualized and adaptive mobile platforms." I think this is interesting but (perhaps unavoidably) vague. Terms like 'learning factors' and 'algorithms' are not very precise. Contrast with the "three main strands of DE research" identified in another IRRODL paper in the same issue: open education, online DE, and educational technology. The topics also overlap, meaning that the same trend is reported more than once by various topics.
Today: 5 Total: 92 [Direct link] [Share]
