As a major carbon-emitting country, there is an urgent need for China to reduce carbon emissions. Studying the carbon emission efficiency of each province helps us to learn about the characteristics and evolution of regional carbon emissions, which is important for proposing effective and targeted measures to achieve the carbon peaking and carbon neutrality goals. This paper measures the carbon emission efficiency of 30 Chinese provinces from 2006 to 2019 based on a three-stage SBM-undesirable model and explores external drivers using stochastic frontier models. The results of the SBM-undesirable model show that the inter-provincial carbon emission efficiency is unevenly distributed and shows a big difference. From the results of the stochastic frontier model analysis, external drivers such as the intensity of finance in environmental protection, the level of economic development, the industrial structure, the level of urbanization, the degree of openness and the level of science as well as technology innovation all have an impact on the emission efficiency. In terms of LSTM model prediction, the model shows an excellent fitting effect, which provides a possible path for carbon emission efficiency prediction. Finally, based on the empirical results and the actual situation of each province in China, this paper proposes relevant feasible suggestions.

In the era of big data, investor sentiment will have an impact on personal decision making and asset pricing in the securities market. This paper uses the Easteconomy stock forum and Sina stock forum as the carrier of investor sentiment to measure the positive sentiment index based on stockholders’ comments and to construct an evaluation index system for the public opinion dimension. In addition, the evaluation index system is constructed from four dimensions, which include operation, innovation, finance and financing, to evaluate the overall condition of listed companies from multiple perspectives. In this paper, the SBM model in the data envelopment analysis method is used to measure the efficiency values of each dimension of the multidimensional efficiency evaluation index system, and the efficiency values of each dimension are the multidimensional efficiency indicators. Subsequently, two sets of input feature indicators of the SVM model were established: one set contains traditional financial indicators and multidimensional efficiency indicators, and another set has only traditional financial indicators. The early warning accuracy of the two sets of input feature indicators was empirically analyzed based on the support vector machine early warning model. The results show that the early warning model incorporating multidimensional efficiency indicators has improved the accuracy compared with the early warning model based on traditional financial indicators. Then, the model was optimized by the particle swarm intelligent optimization algorithm, and the robustness of the results was tested. Moreover, six mainstream machine learning methods, including Logistic Regression, GBDT, CatBoost, AdaBoost, Random Forest and Bagging, were used to compare with the early warning effect of the DEA–SVM model, and the empirical results show that DEA–SVM has high early warning accuracy, which proves the superiority of the proposed model. The findings of this study have a positive effect on further preventing and controlling the financial crisis risk of Chinese-listed companies and promoting as well as facilitating the healthy growth of Chinese-listed companies.

Addressing global climate change has become a broad consensus in the international community. Low-carbon economic development, as an effective means to address global climate change issues, has been widely explored and practiced by countries around the world. As major carbon emitting countries, there has been much focus on China, Japan and South Korea, and it is of practical significance to study their low-carbon economic development. To further measure their trend of low-carbon economic development, this paper firstly constructs a low-carbon economic efficiency evaluation index system and uses the Slack Based Measure (SBM) model. This is a kind of data envelopment analysis (DEA) method, with undesirable output based on global covariance to measure the low-carbon economic efficiency of 94 provincial-level administrative divisions (PLADs) in China, Japan, and South Korea from 2013 to 2019. Subsequently, this paper uses 10 mainstream machine learning models and combining them with Grid Search with Cross Validation (GridSearchCV) methods, selects the machine learning model with the best prediction effect. The model predicts the low-carbon economic efficiency of PLADs in China, Japan, and South Korea from 2020 to 2024 based on the parameter configuration for the best prediction effect. Finally, according to the research results, this paper proposes targeted advice for regionalized cooperation on low-carbon economic development in China, Japan, and South Korea to jointly address global climate change issues.

Analyzing, evaluating, and predicting the trend of globalization are highly valuable endeavors. However, existing literature lacks a quantifiable metric for objective evaluation. To fill the gap, we first compiled a Globalization Index based on existing globalization indices and using the CRITIC weighting method. Second, we constructed the Globalization Barometer and a trend term for trend analysis using the HP filtering method. Third, we conducted time-series predictions for globalization trajectory by applying the Random Forest model. Our results indicate that: (1) The de facto and de jure globalization both displayed a gradually upward trend over time; (2) the 2008 financial crisis and the 2020 COVID-19 pandemic negatively impacted globalization and served as turning points; (3) on a positive note, COVID-19 has narrowed the gap in both de facto and de jure globalization. This is due to the fact that the shocks were uneven, with economies that participated more in globalization weathering the brunt of the impact, while economies that participated less experiencing little changes; (4) the de facto and de jure globalization are predicted to remain on an upward trend for the subsequent 5 years. This research provides essential references for assessing and predicting globalization trends.

Research on the geographical aspects of the digital economy is valuable. We base our study on 10 consecutive years of panel data from 2011–2020 for 31 Chinese provinces. First, we measure the Digital Economy Index using the entropy weight method and analyze its spatiotemporal heterogeneity characteristics using the Exploratory Spatial Data Analysis (ESDA) method. Next, the Grey Model (GM) is utilized to conduct time series predictions of each geographical unit. Finally, we use the GM predicted values and Geographic Weighted Regression (GWR) model to explore the spatial heterogeneity effects of external factors. This study finds that: (1) The overall development shows a trend of vigorous growth, with significant spatial heterogeneity. The gradient difference shows a decreasing trend from the eastern coastal areas to the western inland areas. (2) There is an obvious “digital divide” and a “Matthew effect” in regional development, with agglomeration and spillover effects gradually increasing. (3) Considering the influencing factors, technological progress has a positive impact, and the technology-oriented spatial spillover is obvious, showing a pattern of high in the south and low in the north. The industrial structure is significantly positive, and increases year by year, showing a distribution characteristic of high in the north and low in the south in general, with a clear effect of reducing the “bipolar” distribution. The marginal effects of government support and foreign investment are reduced and there is spatial non-stationarity. This study provides a scientific basis for further research on the spatial development of the digital economy.

Introduction: This study investigates the determinants of women's football viewership by comparing stadium attendance and online streaming demand in the Chinese Women's Super League during the 2023 season. Methods: Match-level data were analyzed using ordinary least squares regression for 125 games with attendance records and negative binomial regression for 126 games with streaming data. Results: The results revealed distinct drivers across the two forms of consumption. Higher stadium attendance was associated with the home team's historical championships, lower per capita disposable income in the host city, and weekend scheduling. In contrast, online streaming demand was shaped by competitive balance and team quality, as well as seasonal variation and the length of time replay videos remained accessible. Discussion: These findings demonstrate that live attendance is influenced primarily by structural and contextual factors, whereas digital audiences respond more directly to match competitiveness and content availability. The study highlights the complementary nature of in-person and digital engagement in women's football and underscores the growing role of data-driven approaches in advancing audience research. By integrating audience behavior analysis with innovations in digital technology, wearable monitoring, and artificial intelligence, this research contributes to the development of interdisciplinary frameworks that can enhance fan engagement, expand the visibility of women's football, and support broader applications of sports science in the digital era.