Publication Date
Summer 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Teng-Sheng Moh
Keywords
Argument Classification, BERT, Discourse Analysis, Feature En- gineering, Machine Learning, Model Optimization, Multiparty Meetings, Natural Language Processing, Neural Networks, Relation Classification.
Abstract
In multi-party meetings, accurately analyzing dialogue is crucial for enhancing communication effectiveness and decision-making. However, the informal and dynamic nature of these discussions presents complex challenges for computational analysis. Dialogues in such settings often include non-standard language, interruptions, and rapid topic changes, making it difficult to extract useful information with conventional text analysis tools. To tackle this challenge, two specific methods were developed:
Argument Classification: We use machine learning models like Gradient Boosting to identify and categorize the main points people make in their discussions. This helps us understand what each person is trying to say, making it easier to follow the conversation and gather useful insights.
Relation Classification: To decipher the complex web of interactions within discussions and map relations between them, we utilize advanced neural network architectures, including BERT (Bidirectional Encoder Representations from Transformers).
The argument classification model achieves an F1 score of 0.79, marking a 28% increase in performance. Similarly, our relation classification model sets a bench mark in the field, with an overall accuracy of 0.86 and an F1 score of 0.83, highlighting its effectiveness in identifying and understanding the nuances of conversational connections. These results highlight the effectiveness of our models in accurately classifying arguments and relationships within meeting transcripts. By identifying these elements, our approach lays the groundwork for transforming raw dialogue into structured data, which can potentially enhance understanding and facilitate better decision-making.
Recommended Citation
Vaitla, Vishal, "Advancing Discourse Analysis in Multiparty Meetings: Comprehensive Classification of Argument and Relation Types" (2024). Master's Projects. 1420.
DOI: https://doi.org/10.31979/etd.5ehn-4qzw
https://scholarworks.sjsu.edu/etd_projects/1420
