Self-reported binary gender prediction from personality traits: Alignment between machine learning importance and classical effect sizes.

Mpox is a zoonotic disease caused by the mpox virus, which belongs to the poxvirus family [,]. The virus can be transmitted directly through contact with lesions, respiratory secretions, or prolonged close person-to-person contact []. The first human case of mpox was detected in the Democratic Republic of Congo in 1970 []. Since then, human mpox has been considered endemic in Central and West Africa, with regular outbreaks in poorer and neglected communities [,]. Sporadic outbreaks caused by mpox did not attract attention until May 2022, when a cluster of mpox cases involving dozens of UK residents was reported []. On 23 July 2022, the World Health Organization declared the mpox outbreak a public health emergency of international concern []. This is the first time human mpox has occurred on a large scale way across continents, with sustained local person-to-person transmission []. It is worth noting that high prevalences of HIV and other sexually transmitted infections have been reported in the global mpox outbreak, which has disproportionately affected primarily gay, bisexual, and other men who have sex with men (MSM) []. The first imported mpox case in mainland China was reported in Chongqing on September 16, 2022 []. This incident immediately sparked intense discussion on Chinese social media. A cross-sectional online survey found that the Chinese public had insufficient mpox knowledge [], while another survey of MSM in China showed that 69.9% reported awareness of mpox []. Given that this incident triggered widespread emotional expression on social media, real-time monitoring and analysis of public sentiment are particularly important. Public emotions play a central role in the dissemination of information during public health emergencies. According to the Crisis and Emergency Risk Communication model, emotional responses, such as fear, anxiety, and anger, directly influence public risk perception, information-seeking behavior, and adoption of protective measures []. The rapid spread of negative emotions can lead to panic, stigmatization, and even irrational behaviors, thereby hindering effective epidemic control efforts. Therefore, real-time monitoring and guidance of public emotions during the critical window following an outbreak announcement is a core task of risk communication. However, existing research has largely focused on the content and themes of public discourse, with insufficient attention paid to emotional dynamics themselves, particularly in non-Western social media environments. Sina Weibo, as China’s leading real-time social media platform with over 462 million users, provides a unique data source for studying public emotional responses []. Weibo comments not only reflect the public opinion on events but also contain rich emotional information, which can be classified as positive, negative, or neutral [,]. Emotional transmission on the Internet often directly affects behavior change. Sentiment analysis, using natural language processing (NLP) and text mining to analyze emotionally subjective texts [], has been widely applied in public health research. One of the important applications is to help guide public opinion and calm emotions during major events (such as extreme events, disaster events, etc.) []. While an increasing number of studies have examined public sentiment during the COVID-19 pandemic [], similar research in the context of mpox outbreaks remains limited, particularly in the Chinese social media environment. A preliminary analysis of this event was published in Chinese by our group using the Weibo platform’s built‑in sentiment module []. The present study differs from that prior work in terms of both methodology and dataset. Methodologically, we used independent data collection, BosonNLP‑based scoring with manual validation, temporal segmentation, Latent Dirichlet Allocation (LDA) topic modeling, and correlation analysis. Regarding the dataset, we analyzed originally crawled comment texts rather than aggregated platform data. The report of the first imported mpox case in mainland China provides a valuable opportunity to investigate real-time emotional dynamics in non-Western social media environments.