Framing Fertility: A Topic Modeling Analysis of Chinese Media Discourse on the Three-Child Policy (2021–2025)

China's Three-Child Policy, announced in 2021, represents the most recent effort by the Chinese government to address the country's prolonged low fertility rate and aging demographic structure. While existing literature has examined the policy from a demographic and policy design perspective, relatively little attention has been paid to how news media, as a critical intermediary between policymakers and the public, frame and respond to the Three-Child Policy. Using a corpus of 3,339 Chinese news articles published between May 2021 and April 2025, this study applies natural language processing (NLP) techniques—specifically Latent Dirichlet Allocation (LDA) topic modeling—to identify domi- nant themes and perspectives in media coverage. Results show that economic concerns, such as labor force shortages and financial burdens associated with childrearing, are central to media discourse. The media also increasingly acknowledge public needs around childcare, housing, and healthcare; however, deeper issues such as persistent gender inequality in caregiving expectations remain under-addressed. This paper argues that without a more gender-equitable reframing in both policy design and public discourse, the Three-Child Policy's long-term effectiveness may be undermined. The study contributes to the growing field of fertility policy research by offering an empirical analysis of media narratives and their social implications.