In order to reveal the manifestations and mechanisms of the cross-language and cross-platform financial digital divide in the social media era, this study is supported by the theory of digital divide, media richness and platform affordances, selects 35,000 financial texts from 10 Chinese and English platforms, uses the unified fine-tuned bilingual FinBERT model combined with statistical testing, and conducts empirical research through progressive hypothesis verification. The research ensures comparability through unified corpus fine-tuning and cross-language alignment, and systematically tests the effects of language, platform, and their interaction. The results show that: Chinese users have lower financial terminology coverage, higher semantic ambiguity, and a gap in expression ability; algorithmic platforms are more likely to disseminate highly emotional and low-professional content, forming an information quality gap; language and platform interact significantly, and language itself is an independent influencing factor of the cognitive empowerment gap. This study expands the cross-linguistic research perspective on the financial digital divide, improves the quantitative measurement method of literacy, provides empirical support for platform optimization, financial science popularization and inclusive finance policy formulation, and points out the research limitations and follow-up directions.
References
[1]
Gupta, S. and Chen, H. (2020) Social Media and Financial Information Ecosystem: A Systematic Review. Journal of Business Ethics, 165, 457-478.
[2]
Chu, Y., Li, M. and Wang, H. (2022) A Comparative Study of Financial Information Sharing on Chinese and English Social Media Platforms. Journal of Computer-Mediated Communication, 27, 892-910.
[3]
Van Dijk, J. (2006) The Deepening Divide: Inequality in the Information Society. Sage Publications. https://doi.org/10.4135/9781452229812
[4]
Yang, C., Zhang, Y. and Liu, J. (2020) Cross-Lingual Adaptability of FinBERT Model in Financial Text Analysis. IEEE Transactions on Knowledge and Data Engineering, 34, 3892-3905.
[5]
Husin, N. (2024) Social Media Content and Youth Financial Decision-Making: A Quantitative Analysis. Journal of Youth Studies, 28, 213-235.
[6]
Hofstede, G. (2011) Dimensionalizing Cultures: The Hofstede Model in Context. Online Readings in Psychology and Culture, 2, 1-26. https://doi.org/10.9707/2307-0919.1014
[7]
Stolper, O.A. and Walter, A. (2017) Financial Literacy, Financial Advice, and Financial Behavior. Journal of Business Economics, 87, 581-643. https://doi.org/10.1007/s11573-017-0853-9
[8]
Vassilakopoulou, A. and Hustad, J. (2023) Algorithmic Bias and Financial Digital Divide in the Social Media Era. New Media & Society, 25, 1456-1478.
[9]
Li, Z. and Wang, L. (2023) Integrating NLP Technology with Social Science Theories: A Case Study of Financial Digital Inequality Research. Social Science Computer Review, 41, 789-806.
[10]
Daft, R.L. and Lengel, R.H. (1986) Organizational Information Requirements, Media Richness and Structural Design. Management Science, 32, 554-571. https://doi.org/10.1287/mnsc.32.5.554
[11]
Kim, J., Lee, S. and Park, H. (2021) Cross-Platform Differences in Information Dissemination: A Perspective of Media Richness Theory. Journal of Communication, 71, 289-312.
[12]
Angelica, M., Rossi, F. and Verdi, C. (2023) The Impact of Social Media Financial Content on Financial Literacy Enhancement. Journal of Consumer Affairs, 57, 189-210.
[13]
Lu, Y., Chen, J. and Zhang, Q. (2023) Internet Infrastructure and Rural Financial Inclusion in China. China Economic Review, 79, Article 101892.
[14]
Lusardi, A. and Mitchell, O.S. (2014) Financial Literacy and Planning: Implications for Retirement Wellbeing. Journal of Economic Perspectives, 28, 43-60.
[15]
Aissaoui, M. (2022) Objective Measurement of Financial Literacy Using Digital Behavioral Data. Journal of Financial Counseling and Planning, 33, 156-172.
[16]
Bucher, T. and Helmond, A. (2018) The Work of Platforms: Reflexivity and the New Media Event. Information, Communication & Society, 21, 22-39.
[17]
Burke, K. and Hung, M. (2021) User Engagement in Online Learning Communities: Integrating Media Richness and Affordance Theory. Computers & Education, 175, Article 104389.
[18]
Kim, H., Park, J. and Lee, J. (2021) Research Gaps in Cross-Platform Information Behavior Studies. Library & Information Science Research, 43, Article 101032.
[19]
Huang, Y., Wang, S. and Li, C. (2023) A Multidimensional Evaluation Framework for Financial Information Quality on Social Media. Journal of Management Information Systems, 40, 567-598.
[20]
Amaral, G. and Kolsarici, C. (2020) A Meta-Analysis of Financial Literacy Measurement Methods. Journal of Economic Surveys, 34, 890-912.
[21]
Gordon, M.L., Lam, M.S., Park, J.S., Patel, K., Hancock, J., Hashimoto, T., et al. (2022) Jury Learning: Integrating Dissenting Voices into Machine Learning Models. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems (CHI ’22), Article No.115, 1-19. https://doi.org/10.1145/3491102.3502004
[22]
Araci, D. (2019) FinBERT: Financial Sentiment Analysis with Pre-Trained Language Models. http://arxiv.org/abs/1908.10063
[23]
Huang, A.H., Wang, H. and Yang, Y. (2023) FinBERT: A Large Language Model for Extracting Information from Financial Text. Contemporary Accounting Research, 40, 806-841. https://doi.org/10.1111/1911-3846.12832
[24]
Liu, Y., Chen, X. and Wang, Z. (2020) Comparative Analysis of FinBERT and General BERT in Financial Text Processing. Journal of Financial Data Science, 2, 78-92.
[25]
Fjellstrom, M. (2022) Stock Market Volatility Prediction Using FinBERT and LSTM Model. Journal of Forecasting, 41, 987-1002.
[26]
Chin, T., Lee, K. and Ng, W. (2024) Extracting Investment Signals from Earnings Conference Calls Using FinBERT. Accounting Horizons, 38, 45-62.
[27]
Saunders, M., Lewis, P. and Thornhill, A. (2019) Research Methods for Business Students. 8th Edition, Pearson Education Limited.
[28]
Hair, J.F., Black, W.C., Babin, B.J. and Anderson, R.E. (2014) Multivariate Data Analysis. 8th Edition, Pearson Prentice Hall.
[29]
Hansen, S., McMahon, M. and Prat, A. (2018) Transparency and Deliberation within the FOMC: A Computational Linguistics Approach. The Quarterly Journal of Economics, 133, 801-870. https://doi.org/10.1093/qje/qjx045
[30]
Pan, L., et al. (2020) Cross-Cultural Differences in Financial Discourse: A Corpus-Based Study. Journal of Pragmatics, 155, 120-135.
