Quantum Perspectives on Persuasive Language in AI-Generated News: A QNLP-Based Analysis

Jung-Hua Liu


Abstract
This study applies quantum natural language processing (QNLP) to 298 Chinese AI-generated YouTube news articles. Using IBM Qiskit, we reveal multi-reality narratives with high frame competition but low conflict. Headlines employ emotion, content stays neutral or positive, showing strategic ambiguity. QNLP metrics highlight persuasive tactics and implications for communication theory and AI ethics.
Anthology ID:
2025.rocling-main.39
Volume:
Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
Month:
November
Year:
2025
Address:
National Taiwan University, Taipei City, Taiwan
Editors:
Kai-Wei Chang, Ke-Han Lu, Chih-Kai Yang, Zhi-Rui Tam, Wen-Yu Chang, Chung-Che Wang
Venue:
ROCLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
358–368
Language:
URL:
https://aclanthology.org/2025.rocling-main.39/
DOI:
Bibkey:
Cite (ACL):
Jung-Hua Liu. 2025. Quantum Perspectives on Persuasive Language in AI-Generated News: A QNLP-Based Analysis. In Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025), pages 358–368, National Taiwan University, Taipei City, Taiwan. Association for Computational Linguistics.
Cite (Informal):
Quantum Perspectives on Persuasive Language in AI-Generated News: A QNLP-Based Analysis (Liu, ROCLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.rocling-main.39.pdf