Sentiment Analysis through the Lens of Systemic Functional Grammar: Bridging Linguistic Theory and NLP

Abstract

This paper explores the use of M.A.K. Halliday’s Systemic Functional Grammar (SFG) in sentiment analysis within Natural Language Processing (NLP). Unlike traditional sentiment analysis, which mainly relies on statistical and machine learning approaches, this research aims to connect linguistic theory with computational methods by utilizing SFG to enhance the depth and clarity of sentiment analysis. SFG’s focus on ideational, interpersonal, and textual metafunctions provides a strong framework for understanding how sentiment is expressed in text. By thoroughly examining these metafunctions, the paper shows that SFG can effectively recognize subtle sentiment nuances often missed by conventional techniques. It employs both qualitative and quantitative methods to analyze sentiment data, highlighting SFG’s potential to improve the accuracy and interpretability of sentiment analysis. The findings emphasize the advantages of integrating linguistic theory into NLP and suggest directions for future research in this interdisciplinary area.