doi: 10.18178/joebm.2026.14.4.961
AI-Enabled Sentiment Monitoring for Human-Supervised Cross-Market Wealth Management between Mainland China and Hong Kong
Huaye Zhang
- Faculty of Business, Lingnan University, Hong Kong, China
- Manuscript received August 6, 2026
- accepted October 2, 2026
- published October 27, 2026
Abstract
The investor sentiment can amplify short-term risks and complicate wealth decisions, especially with global themes of rapid change and volatility. This paper presents an event-driven empirical proof-of-concept of AI-driven sentiment tracking as human-assisted wealth management in Mainland China and Hong Kong. A pre-trained Chinese financial sentiment classifier labels 70 dated A-Dame market-news headlines and 28 dated Hong Kong market-news reports as positive, neutral, or negative. Headline-level tone is aggregated into daily and event-window measures of everyday and event-time frame tone and compared to CSI300 and Hang Seng index. Three event-windows are studied: 2023 panic-and-recover window, 2024 sentiment-reward and high volatility window, and 2525 tech flair and trading on volatility window Positive during 2023 window, and negative window in Hong Kong, both positive in 2024 sentiment-reward window, Hong Kong sentiment stronger, negative in 25 tech flair window in Hong Kong, neutral in mainland. Risks varied by event-windows. 2024 window was high volatility in both locations and the deepest average post-event drawdowns period, however, later-stage risks varied in profile. Rather, they support the use of AI-derived news signals as a structured prompt for human review of concentration, liquidity, and cross-market diversification decisions.
Keywords
- AI sentiment analysis
- wealth management
- A-share market
- Hong Kong market
- investor sentiment
How to Cite
Huaye Zhang, "AI-Enabled Sentiment Monitoring for Human-Supervised Cross-Market Wealth Management between Mainland China and Hong Kong," Journal of Economics, Business and Management, vol. 14, no. 4, pp. 306-311, 2026. https://doi.org/10.18178/joebm.2026.14.4.961
Copyright & License
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).