Using Natural Language Processing to Analyze Tutorial Dialogue Corpora Across Domains and Modalities

摘要

Our research goal is to investigate whether previous findings and methodsudin the area of tutorial dialogue can be generalized across dialogue corpora thatuddiffer in domain (mechanics versus electricity in physics), modality (spoken versusudtyped), and tutor type (computer versus human). We first present methods forudunifying our prior coding and analysis methods. We then show that many of ourudprior findings regarding student dialogue behaviors and learning not only generalizeudacross corpora, but that our methodology yields additional new findings. Finally,udwe show that natural language processing can be used to automate some ofudthese analyses.