Your Justice Is Different From My Justice: Quantifying Mental State Variation of Identical Words Through a Case Study of Korean Newspaper Corpora

Abstract

This study offers a quantitative investigation of a well-established question in theoretical linguistics: how identical words can carry subtle semantic variations across different contexts. While linguists have long recognized this phenomenon, empirical measurement has been elusive. Using computational linguistic techniques, this research analyzes politically contrasting two Korean newspapers as corpora to demonstrate and quantify how lexical meanings are shaped by surrounding context. Three methods were employed: Latent Semantic Analysis, Topic Modeling, and Sentiment Analysis. The findings provide empirical support for theoretical concepts of fluid word meanings. Both abstract and concrete words exhibited measurable context-dependent semantic shifts, with concrete words showing stronger sentimental biases. This approach to quantifying lexical semantics contributes to the validation of linguistic theories and opens new avenues for exploring language use across various domains. The results have potential implications for cross-cultural communication, language acquisition, and media practices.



Author Information
Hana Jee, York St John University, United Kingdom

Paper Information
Conference: MediAsia2024
Stream: Education and Scholastic Journalism

This paper is part of the MediAsia2024 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window


To cite this article:
Jee H. (2024) Your Justice Is Different From My Justice: Quantifying Mental State Variation of Identical Words Through a Case Study of Korean Newspaper Corpora ISSN: 2186-5906 – The Asian Conference on Media, Communication & Film 2024: Official Conference Proceedings (pp. 61-72) https://doi.org/10.22492/issn.2186-5906.2024.5
To link to this article: https://doi.org/10.22492/issn.2186-5906.2024.5


Virtual Presentation


Comments & Feedback

Place a comment using your LinkedIn profile

Comments

Share on activity feed

Powered by WP LinkPress

Share this Research

Posted by James Alexander Gordon