Speech act classification in computational linguistics using supervised machine learning models
Shadi Dini, Penny L. Hammrich, Aroutis N. Foster · 2023
This dissertation utilizes two supervised machine learning models, Random Forest and Support Vector Machine (SVM), to classify speech acts, specifically direct and indirect Requests and Refusals, in a dataset of over 5000 emails. The study focuses on analyzing asynchronous communications, particularly emails, as authentic sources of data. By comparing the performance of Random Forest and SVM, the research demonstrates that SVM outperforms Random Forest in accurately classifying both direct and indirect speech acts. The findings have significant implications for various fields, including linguistics, natural language processing, and education, highlighting the potential of SVM in speech act classification tasks and its contribution to the analysis of conversational data.