Jian Yao

In live-streaming e-commerce systems, massive volumes of user-generated danmaku constitute a critical yet underutilized source of business intelligence. However, transforming such unstructured, noisy, and highly context-dependent textual data into structured and actionable knowledge remains a fundamental challenge for enterprise information systems. To address this issue, this study proposes TaSC-LLM, an LLM-enabled topic recognition method for constructing interpretable topic measurements from unstructured user-generated content. The proposed framework integrates topic taxonomy construction and zero-shot classification into a unified semantic reasoning pipeline. Unlike conventional topic modeling or supervised classification approaches, TaSC-LLM leverages chain-of-thought reasoning, multi-stage taxonomy induction, sliding window context modeling, and self-consistency verification to eliminate reliance on predefined label spaces and annotated training data. This design allows the system to dynamically construct and update topic taxonomies while ensuring interpretability, robustness, and cross-scenario adaptability. Empirical evaluation on three large-scale live-streaming e-commerce danmaku datasets shows that TaSC-LLM achieves strong taxonomy coverage, classification accuracy, and agreement with expert annotations. The findings suggest that LLM-based reasoning can help convert unstructured user-generated text into interpretable topic measures for downstream empirical and managerial analysis. While the present evaluation is conducted offline, TaSC-LLM provides a methodological foundation for future business applications that can be further examined under multi-session, multi-platform, and deployment-oriented conditions.

This study examines risk connectedness among sustainable and digital assets from 24 September 2019 to 26 May 2025. The sample contains three green finance indices, five literature-based green cryptocurrencies, and five literature-based non-green/conventional cryptocurrencies. We estimate conditional volatility, skewness, and kurtosis using the GARCHSK model and then apply time-domain, frequency-domain, and TVP-VAR connectedness frameworks to identify how shocks are shared across assets, moments, and investment horizons. The results show that the sustainable–digital finance system is strongly connected but unevenly organized. In the baseline static estimates, total connectedness is 75.87 for volatility, 65.11 for skewness, and 77.94 for kurtosis. Volatility and kurtosis connectedness are mainly long-run phenomena, whereas skewness connectedness is split almost evenly between short- and long-run components. Green finance assets mainly occupy net receiver positions in the estimated connectedness network, while several cryptocurrencies, including some classified as green in the literature, appear as net transmitters of volatility or tail-risk connectedness. Additional robustness checks using a monthly frequency cutoff and a pre-/post-Ethereum Merge split support the main horizon-level interpretation while also showing that the strength of connectedness changes across regimes. The findings provide connectedness-based diagnostics for portfolio design, system-level risk monitoring, and governance of sustainable–digital finance. They should be interpreted as evidence on forecast-error variance connectedness and relative transmitter/receiver roles rather than as structural causal estimates or direct measures of systemic losses.