This study employs an integrated analytical framework combining the Social-Ecological System (SES) and Driver-Pressure-State-Impact-Response (DPSIR) models, supplemented by quantitative methodologies including the Entropy Weight Method (EWM), Generalized Additive Model (GAM), Lasso regression, and shallow neural networks, to conduct a systematic resilience assessment of six representative Tibetan villages in western Sichuan based on longitudinal data from 2015 to 2022. The analysis reveals significant differences in resilience levels among the villages, primarily influenced by multiple factors. Disposable income and employment are key positive drivers that enhance adaptive capacity and resilience. Conversely, excessive reliance on policy interventions may constrain local self-organization and adaptive governance. The study highlights the complexity of balancing ecological sustainability with economic growth, underscoring the need for flexible and inclusive policy frameworks. Furthermore, the findings indicate that integrating top-down policies with community-based governance can effectively mitigate external pressures. Key recommendations involve promoting economic diversification via agroecology and cultural tourism, enhancing local governance capacity, and adopting adaptive environmental policies. These strategies are crucial for reducing dependence on traditional agriculture and alleviating resource pressures. The insights gained from this study deepen the understanding of restoration mechanisms in ecologically fragile areas and contribute to the development of effective strategies for sustainable management.

With the rapid development of digital technology, "metaverse" has gradually entered the public's field of vision, and has begun to build metaverse platforms in various fields. As one of the products of the metaverse, the virtual idol is becoming more and more popular, not only becoming the object of many fans, but also becoming the new darling of the industry. The new digital technology has not only updated the form of virtual idol, but also affected the creative method and participation mode of virtual idols with continuous changes, so that fans have a more immersive "star-following" experience. The interactive behavior and emotional cognition of fans are also constantly changing with the development of digital technology. This paper will summarize the role of digital technology in the transmission of virtual idols, explore the role of digital technology in the relationship between virtual idols and fans, and look forward to the influence trend of the development of digital technology on virtual idols through analysis.

Sentiment words play an important role in sentiment classification research. In sentiment analysis and classification research, sometimes it is necessary to obtain as many sentiment words as possible. Open source word vector datasets usually have a huge vocabulary that contains rich sentiment words. Sentiment words can be obtained using vectors and a large number of words in open source word vectors. In this paper, given sentiment words, such as sentiment words in the dictionary, are used as seed words, and then the word similarity algorithm is used. From the open source word vector data set, the words similar to the target sentiment words are searched, and the sentiment words are obtained through manual labeling and filtering. Experiments show that this method is an efficient and low-cost method to obtain sentiment words.

In the case of COVID-19 epidemic, online education supported by computing technology is playing an increasingly important role, while online education resources, especially micro-lectures, are seriously insufficient, which greatly hinders the development of online education. In this paper, a micro-lecture resource construction scheme for online courses with teacher-student collaboration was proposed based on the learning pyramid theory. The practice proved that this scheme can make full use of students’ technical foundation in the Internet era to build micro-lectures, which can not only improve the quality of online courses, but also build curriculum resources quickly and with high quality, thus providing a strong resource guarantee for the follow-up online teaching.