Comparative Study on the Discourse Meaning of Chinese and English Media in the Paris Olympics Based on LDA Topic Modeling Technology and LLM Prompt Engineering
Yinglong Yu, Zhaopu Yao, Fang Yuan
TL;DR
The study addresses how Chinese and English media frame the Paris Olympics and the attitudinal meanings embedded in coverage. It integrates LDA topic modeling with LLM-based prompt engineering to extract topics and generate interpretive descriptions, then employs extended meaning units and semantic prosody analysis to compare macro-level discourse and micro-level keyword patterns. Key findings show both languages foreground the opening ceremony, events, and sponsorship, but Chinese coverage emphasizes national sport achievements, Olympic spirit, doping discussions, and new technologies, while English coverage emphasizes female athletes and eligibility controversies. The combined approach demonstrates a scalable, cross-language framework for rapid discourse analysis with practical implications for media literacy and international communications, and it suggests directions for refining prompt designs and deeper EMU-based interpretation.
Abstract
This study analyzes Chinese and English media reports on the Paris Olympics using topic modeling, Large Language Model (LLM) prompt engineering, and corpus phraseology methods to explore similarities and differences in discourse construction and attitudinal meanings. Common topics include the opening ceremony, athlete performance, and sponsorship brands. Chinese media focus on specific sports, sports spirit, doping controversies, and new technologies, while English media focus on female athletes, medal wins, and eligibility controversies. Chinese reports show more frequent prepositional co-occurrences and positive semantic prosody in describing the opening ceremony and sports spirit. English reports exhibit positive semantic prosody when covering female athletes but negative prosody in predicting opening ceremony reactions and discussing women's boxing controversies.