Developing an early warning model for company financial crises holds critical significance in robust risk management and ensuring the enduring stability of the capital market. Although the existing research has achieved rich results, the disadvantages of insufficient text information mining and poor model performance still exist. To alleviate the problem of insufficient text information mining, we collect related financial and annual report data from 820 listed companies in mainland China from 2018 to 2023 by using sophisticated web crawlers and advanced text sentiment analysis technologies and using missing value interpolation, standardization, and data balancing to build multi-source datasets of companies. Ranking the feature importance of multi-source data promotes understanding the formation of financial crises for companies. In the meantime, a novel Attention-based Fuzzy Neural Network (AFNN) was proposed to parse multi-source data to forecast financial crises among listed companies. Experimental results indicate that AFNN exhibits significantly improved performance compared to other advanced methods.

Corporate site visits provide investors with opportunities to obtain non-standard, tailored "soft" information about the firm. In this study, we investigate the impact of information disclosed from corporate site visits on stock market stability from the perspective of stock return volatility. Our findings suggest that it is the information disclosed rather than the visits themselves that significantly reduce stock return volatility, primarily by mitigating information asymmetry. Moreover, we observe that the volatility-mitigating effect of site visits is more pronounced when the visit information better aligns with investors' concerns and when it is more effectively disseminated. Our study contributes to the literature by demonstrating that the timely disclosure of site visit details serves as a stabilizing mechanism for stock prices through effective information mining and dissemination.