This study introduces the Constructed Response Analysis Tool (CRAT), a freely available tool to automatically assess student responses in online tutoring systems. The study tests CRAT on a dataset of chemistry responses collected in the ChemVLab+. The findings indicate that CRAT can differentiate and classify student responses based on semantic overlap with student input and indices related to word frequency, text content, and lexical sophistication. Overall, the findings suggest that more accurate student responses show greater overlap with the content learned, include more academic function words, contain greater content that is descriptive, and includes more specific and familiar words. [For the full proceedings, see ED592609.]