Abstract: Time and resources constrain instructors from using constructed-response (essay) assessments in large undergraduate science courses, resulting in multiple choice assessments predominating. However, open-response assessments are often better at revealing student thinking and conceptual barriers. Computerized tools can analyze open-responses with a level of accuracy that gives instructors the richness of information they need to understand the learning status of their students. Using assessments about weak and strong acids, we show how combined Lexical and Discriminant Analyses are capable of predicting, with 86% accuracy, how an expert human scorer would classify student responses. This can provide a powerful tool for instructors in large courses to follow the learning status of their students at a level of detail previously not available. Sample Assessment: Weak and Strong Acids
Publication Year: 2008
Publication Date: 2008-01-01
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot