Using Natural Language Processing to Inform Science Instruction (Collaborative Research: Linn)

NLP-TIPS takes advantage of natural language processing (NLP) methods to detect students’ ideas in written science explanations. We design adaptive guidance that supports each student to consider their own ideas and pursue deeper understanding of phenomena. This work continues a successful partnership between University of California, Berkeley, Educational Testing Service (ETS), and science teachers from schools enrolling students from diverse racial, ethnic, and linguistic groups whose cultural experiences may be neglected in science instruction.