The Relative Contribution of Language Complexity to Second Language Video Lectures Difficulty Assessment

Although core in the teaching of academic language skills, little research to date has investigated what makes video-recorded lectures difficult for learners. As part a larger program develop automated videotext complexity measures, this study reports on selected dimensions linguistic understand how they contribute overall difficulty. Based ratings English learners 320 video lectures, we built regression models predict subjective estimates lecture The results our analysis demonstrate that 4-component partial least square model explains 52% variance difficulty and significantly outperformed baseline predicting videos an out-of-sample testing set. point use features raise possibility developing systems measuring difficulty, akin those already available estimating readability written materials.