Background HPV vaccination rate is low in China. Understanding the multidimensional barriers and impetuses perceived by individuals to vaccination is essential. We aim to assess the public perceptions, perceived barriers, and facilitators towards HPV vaccination expressed on Chinese social media platform Weibo. Methods We collected Weibo posts regarding HPV vaccines between 2018 to 2023. We annotated 6,600 posts manually according to behavior change theories, and subsequently fine-tuned deep learning models to annotate all posts collected. Based on the annotated results of deep learning models, temporal and geographic analyses were conducted for public attitudes towards HPV vaccination and its determinants. Findings Totally 1,972,495 Weibo posts were identified as relevant to HPV vaccines. Deep learning models reached predictive accuracy of 0.78 to 0.96 in classifying posts. During 2018 to 2023, 1,314,510 (66.6%) posts were classified as positive attitudes. And 224,130 posts (11.4%) were classified as misinformation, 328,442 posts (16.7%) as perceived barriers to accepting vaccines, and 580,590 posts (29.4%) as practical barriers to vaccination. The prevalence of positive attitude increased from 15.8% in March 2018 to 79.1% in mid-2023 (p < 0.001), and misinformation declined from 36.6% in mid-2018 to 10.7% in mid-2023 (P < .001). Central regions exhibited higher prevalence of positive attitudes and social norms, whereas Shanghai, Beijing megacities and northeastern regions showed higher prevalence of negative attitudes and misinformation. Positive attitudes were significantly lower for 2-valent vaccines (65.7%), than 4-valent or 9-valent vaccines (79.6% and 74.1%). Interpretation Social media listening represents a promising surveillance approach for monitoring public perceptions on health issues and can enable the development of health communication strategies.

ZH received funding from Merck Investigator Initiated Studies. The other authors declare no competing interests.

ZH acknowledges financial support from Merck Investigator Initiated Studies (61185). The funders had no role in the study design, data collection, data analysis, data interpretation, or writing of the report.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The study used ONLY openly available human data that were originally presented at Weibo social media platform. The study was approved by the Institutional Review Board of the School of Public Health, Fudan University (IRB#2022-01-0938).

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

All data described in the results and corresponding Python/R codes will be shared on GitHub upon acceptance of this paper. Original posts are not shared according to Weibo's data policy. Other data are available on request from the corresponding author.