Generating content for large-scale reading comprehension assessments, particularly stories, poses significant challenges including money, time, and effort. To serve as effective assessment tools, these comprehension stories must adhere to specific criteria defined in early grade reading assessment standards dictating narrative structure, character types, readability levels, and other elements. Recently Natural Language Processing (NLP) techniques, mainly Large Language Models (LLMs), have been used to automate the story generation process. One key challenge is ensuring diversity across the many generated stories. For example, the Early reading standards such as Early Grade Reading Assessment (EGRA) requires comprehension stories to be similar in difficulty level but narratively different across multiple implementations to ensure fairness. This paper proposes a solution to increase diversity across stories by employing GPT-4 to generate children’s reading comprehension stories mediated by a database of classic tales. By leveraging existing narratives, this method drastically reduces the resources required for content creation while ensuring alignment with the EGRA criteria. We present a systematic framework for selecting, adapting, and evaluating the stories, aiming to streamline the content generation process. The generated stories are additionally evaluated using well-defined text metrics and by a human evaluator for reliability. Our findings underscore the potential of integrating GPT-4 with classic tales to optimize resources and enhance scalability in literacy assessment practices, offering practical implications for educators and policymakers in early grade learning.

Classroom observation is an important tool for improving quality of education. Observations allow teacher trainers to monitor, assess, and provide feedback to teachers about their teaching techniques and class management practices. The current approach to class observation consists of an observer visiting a classroom once or twice a year. This is both costly in terms of time and resources, insufficient in terms of capturing the true state of the classroom, and in providing accurate feedback. This paper presents the design and implementation of a mobile-based system that automates the class observation process using data mining techniques. The system allows teachers to record audio snapshots during the class session, and receive Stallings-type analysis results for their class on a daily basis.