Understanding the Unspoken: A Cross-Cultural AI Framework for Sentiment and Bias Detection

Authors

  • Karmbir HMR Institute of Technology and Management Hamidpur Author
  • Sushil Verma HMR Institute of Technology and Management Hamidpur Author
  • Piyush Gupta HMR Institute of Technology and Management Hamidpur Author
  • Priya HMR Institute of Technology and Management Hamidpur Author
  • Prakhar Pandey HMR Institute of Technology and Management Hamidpur Author

DOI:

https://doi.org/10.21467/proceedings.7.6.54

Keywords:

Artificial Intelligence Sentiment, Analysis Bias Detection, Cross-Cultural Communication

Abstract

In a global world where people are connected by digital communication across continents it has become more critical than ever to understand how emotions and biases are conveyed in various cultural contexts. This analysis delves into the potential of Artificial Intelligence to use sentiment analysis to identify subtle biases in online discourse that cut across cultures and languages. Cultural differences in language e.g. idioms tone context can easily modify the meaning of a message to the extent that it's often challenging to derive meaningful insights with traditional sentiment analysis tools. We address this challenge by developing a framework based on sophisticated NLP methods and deep learning architectures that analyse multilingual text in a culturally aware manner. The system is programmed to detect emotional cues and bias patterns that are commonly overlooked because of linguistic and regional differences. With this method we hope to create AI tools that are not just smarter but also more respectful inclusive and context-sensitive. This study contributes to the current debate regarding ethical AI and emphasizes the need to create systems that more accurately represent the complexity of human communication in a globalized digital environment.

References

[1]. A. Shariq Imran S. M. Doudpota Z. Kastrati and R. Bhatra "Cross-Cultural Polarity and Emotion Detection Using Sentiment Analysis and Deep Learning: A Case Study on COVID-19" arXiv preprint arXiv:2008.10031 Aug. 2020. https://arxiv.org/abs/2008.10031

[2]. Y. Wan and M. Nakayama "A Sentiment Analysis of Star-Rating: A Cross-Cultural Perspective" in Proceedings of the 55th Hawaii International Conference on System Sciences Jan. 2022 pp. 4567-4576.

[3]. T. D. Belay A. H. Ahmed A. Grissom II I. Ameer G. Sidorov O. Kolesnikova and S. M. Yimam "CULEMO: Cultural Lenses on Emotion—Benchmarking LLMs for Cross-Cultural Emotion Understanding" arXiv preprint arXiv:2503.10688 Mar. 2025. https://www.arxiv.org/abs/2503.10688

[4]. R. I. Jahan H. Fan H. Chen and Y. Feng "Unlocking Cross-Lingual Sentiment Analysis through Emoji Interpretation: A Multimodal Generative AI Approach" arXiv preprint arXiv:2412.17255 Dec. 2024. https://arxiv.org/abs/2412.17255

[5]. Y.-M. Cho D. Pang S. Thapa G. Sherman L. Ungar L. Tay and S. C. Guntuku "Language-Based Valence and Arousal Expressions between the United States and China: A Cross-Cultural Examination" arXiv preprint arXiv:2401.05254 Jan. 2024. https://arxiv.org/abs/2401.05254

[6]. H. Zhang Y. Liu and J. Li "Twitter Sentiment Analysis of Cross-Cultural Perspectives on Climate Change" in Proceedings of the 2023 International Conference on Social Computing and Social Media Jul. 2023 pp. 345-356. https://link.springer.com/chapter/10.1007/978-3-031-35936-1_29

[7]. T. D. Belay A. H. Ahmed A. Grissom II I. Ameer G. Sidorov O. Kolesnikova and S. M. Yimam "CULEMO: Cultural Lenses on Emotion—Benchmarking LLMs for Cross-Cultural Emotion Understanding" arXiv preprint arXiv:2503.10688 Mar. 2025. https://arxiv.org/abs/2503.10688

[8]. A. Câmara L. R. Do Couto M. C. Diniz and A. Villavicencio "Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English Spanish and Arabic" arXiv preprint arXiv:2204.03558 Apr. 2022. https://arxiv.org/abs/2204.03558

[9]. S. Goldfarb-Tarrant A. Pandey P. Kumar and R. Sharma "Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis" in Proc. of EMNLP 2023 Dec. 2023 pp. 5691–5704.

[10]. S. Levy A. Stern R. Shwartz and Y. Goldberg "Comparing Biases and the Impact of Multilingual Training across Multiple Languages" arXiv preprint arXiv:2305.11242 May 2023. https://arxiv.org/abs/2305.11242

[11]. P. Přibáň and J. Steinberger "Are the Multilingual Models Better? Improving Czech Sentiment with Transformers" arXiv preprint arXiv:2108.10640 Aug. 2021. https://arxiv.org/abs/2108.10640

[12]. J. P. Venugopal R. Rajesh and R. Sharma "A Comprehensive Approach to Bias Mitigation for Sentiment Analysis of Social Media Data" Applied Sciences vol. 14 no. 23 Dec. 2024. https://www.mdpi.com/2076-3417/14/23/11471

[13]. M. Ahmad S. Zaidi and A. Aslam "Multilingual Sentiment Analysis: Overcoming Challenges in Cross-Language Sentiment Detection with NLP" Int. J. of Contemporary Issues in Social Sciences vol. 3 no. 3 Jul.–Sep. 2024.

[14]. N. Nørgaard T. Lund and K. Sørensen "This New Way to Train AI Could Curb Online Harassment" Wired Jun. 2021.

[15]. M. Roberts and E. Yang "How Censorship Can Influence Artificial Intelligence" Wired Aug. 2019.

Downloads

Published

2025-11-21

Issue

Vol. 7 No. 6 (2025): Proceedings of the 3rd International Conference on Artificial Intelligence, Machine Learning and Cybersecurity

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

How to Cite

[1]
Karmbir, S. Verma, P. Gupta, Priya, and P. Pandey, “Understanding the Unspoken: A Cross-Cultural AI Framework for Sentiment and Bias Detection”, AIJR Proc., vol. 7, no. 6, pp. 475–484, Nov. 2025, doi: 10.21467/proceedings.7.6.54.