Preliminary experiments on crowdsourced evaluation of feedback granularity

Abstract

Providing writing feedback to English language learners (ELLs) helps them learn to write better, but it is not clear what type or how much information should be provided. There have been few experiments directly comparing the effects of different types of automatically generated feedback on ELL writing. Such studies are difficult to conduct because they require participation and commitment from actual students and their teachers, over extended periods of time, and in real classroom settings. In order to avoid such difficulties, we instead conduct a crowdsourced study on Amazon Mechanical Turk to answer questions concerning the effects of type and amount of writing feedback. We find that our experiment has several serious limitations but still yields some interesting results.