The problem
Research ↗ shows that students who consistently engage with complex texts are more likely to succeed in college and beyond. Yet despite their importance, complex texts often remain absent from classrooms.- Quantitative measures of text complexity (e.g., Lexile or Flesch-Kincaid) are useful, but limited
- Qualitative measures are more accurate, but also more labor-intensive to assess
What we’re building
Instead of giving a single complexity score, our literacy evaluators assess text across multiple qualititative dimensions. They are anchored in Student Achievement Partners’ Qualitative Text Complexity rubric (SAP) ↗, giving you:- Fine-grained data to ensure quality generated texts
- Actionable insights into why a text may be complex or not complex enough and how to best scaffold it for students
| Evaluator | Description |
|---|---|
| Grade Level Appropriateness | Determines whether AI-generated text is suitable for a grade band and suggests scaffolding that can support instruction of the text |
| Subject Matter Knowledge | Identifies the background knowledge a student needs to comprehend the generated text |
| Vocabulary | Measures how challenging students may find the vocabulary of AI-generated texts |
| Conventionality | Analyzes how directly a text communicates its meaning |
| Purpose | Assesses how clearly a text communicates its central purpose, and identifies elements that make that purpose accessible or challenging to readers |
| Intertextuality | Assesses what a text assumes you’ve already encountered and then builds on to create meaning |