We present a computational exploration of argument critique writing by young students. Middle school students were asked to criticize an argument presented in the prompt, focusing on identifying and explaining the reasoning flaws. This task resembles an established college-level argument critique task. Lexical and discourse features that utilize detailed domain knowledge to identify critiques exist for the college task but do not perform well on the young students’ data. Instead, transformer-based architecture (e.g., BERT) fine-tuned on a large corpus of critique essays from the college task performs much better (over 20% improvement in F1 score). Analysis of the performance of various configurations of the system suggests that while children’s writing does not exhibit the standard discourse structure of an argumentative essay, it does share basic local sequential structures with the more mature writers.

Automatic identification of good arguments on a controversial topic has applications in civics and education, to name a few. While in the civics context it might be acceptable to create separate models for each topic, in the context of scoring of students’ writing there is a preference for a single model that applies to all responses. Given that good arguments for one topic are likely to be irrelevant for another, is a single model for detecting good arguments a contradiction in terms? We investigate the extent to which it is possible to close the performance gap between topic-specific and across-topics models for identification of good arguments.