Aiming to address the complexity and challenges of predicting pure electric vehicle (EV) sales, this paper integrates a time series model, support vector machine and combined model to forecast EV sales in China. Firstly, a seasonal autoregressive integrated moving average (SARIMA) model was constructed using historical EV sales data, and the model was trained on sales statistics to obtain forecasting results. Secondly, variables that were highly correlated with sales were analyzed using gray relational analysis (GRA) and utilized as input parameters for the support vector regression (SVR) model, which was constructed to optimize sales predictions for EVs. Finally, a combined model incorporating different algorithms was verified against market sales data to explore the optimal sales prediction approach. The results indicate that the SARIMA-GRA-SVR model with the squared prediction error and inverse method achieved the best predictive performance, with MAPE, MAE and RMSE values of 12%, 1.45 and 2.08, respectively. This empirical study validates the effectiveness and superiority of the SARIMA-GRA-SVR model in forecasting EV sales.

For tourism crises, social media present a double-edged sword: while disseminating the damage caused by tourism crises, it also has the potential to enhance the destination’s visibility and serve as a promotional tool. So, we cannot entirely negate the dissemination of tourism crises but rather proactively utilize its positive aspects to promote the sustainable development of the tourism destination image (TDI). Crisis events caused by management mistakes can be particularly damaging to people’s trust in destination management organizations (DMOs), and a crowd crush is a common and highly damaging type of tourism crisis caused by public management mistakes. Thus, the purpose of this study is to summarize the factors that may positively influence TDI in the dissemination of tourism crises such as the Seoul Halloween crowd crush. This study takes the Seoul Halloween crowd crush as an example and constructs a theoretical model based on information ecology theory. The relationships of variables in the model were analyzed through structural equation modeling. The results show that information transparency, subject authority, and social media interactivity positively influence an organic cognitive image. Social connection and social media interactivity positively influence this organic affective image. Finally, this study provides targeted recommendations for DMOs, which is important for the restoration of TDI after crises.