Online reviews are crucial for identifying the factors that affect the dynamic evolution of tourist sentiment, improving tourist satisfaction. This study employs pre-trained models BERT and BERTopic and social network analysis to examine 228,062 reviews collected from Ctrip using Python. The factors influencing tourist sentiment across natural tourism attractions (NTAs), cultural tourism attractions (CTAs), and theme park tourism attractions (TPTAs) were explored before, during, and after the pandemic. The findings reveal that there was minimal change in the types of factors influencing before and during the pandemic, significant changes in the values of factors during the pandemic, and fluctuations in both the types and values of factors after the pandemic. Regardless of the period, influences on negative sentiment were more dispersed, while positive emotions were more polarized. Based on these insights, we propose theoretical contributions and improvement strategies for enhancing resilience and promoting high-quality development in different types of attractions.

Tourist flows, crucial information within online travelogues, reveal the interactive relationships between different tourist destinations and serve as the nerve center and link of the tourism system. This study takes Hangzhou, China, as a case to investigate the spatial network structure of its tourist flows. Firstly, a BERT-BiLSTM-CRF model and pan-attraction database are built to extract tourist attractions from online travelogues and create the tourist flow matrix. Then, this study uses social network analysis (SNA) to examine the structure of the tourist flow network from a county-level perspective. Additionally, GIS spatial analysis methods are applied to analyze the evolution of the tourist gravity center and standard deviation ellipse (SDE) of the network. The results reveal that the identification performances of the tourist flow extraction model this study proposed are significantly better than those of previous mainstream models, with an F1 value of 0.8752. Furthermore, the tourist flow network in Hangzhou displays a relatively sparse and unbalanced distribution, forming a “Core–Semi-Periphery–Periphery” structure. Lastly, from 2020 to 2022, the network’s gravity center experienced a shift towards the southwest, paralleled by an initial expansion and subsequent contraction of the SDE in the same southwest direction. These findings provide valuable insights into the spatial network structure of tourism in Hangzhou and can serve as a reference for policymakers to promote the “all-for-one” tourism.