While the salience of social media platforms on modern interactive communication between diverse social actors has been demonstrated, less academic attention has been paid to comparisons between framed topics and user interactions across social media platforms, such as Twitter and Weibo. This article suggests text mining and natural language processing tools for cross-platform comparative social media studies, based on Latent Dirichlet Allocation (LDA) and social network analysis. This study illustrates how the suggested topic models and data processing algorithms can be applied to a real-life example (U.S.-China trade war discourse on social media), and experimented the methods on social media text mining data, revealing differences between user interactions on Twitter, predominantly "Western," and Weibo, largely representing Chinesespeaking users. We discuss the strengths and weaknesses of the suggested machine learning algorithms for comparative social media studies.

The advent of digital social media in China has altered our understanding of who sets the policy agenda and forms public opinion. Using text mining analysis of more than 74,000 Weibo user comments (over 4 million words) on 6 years' worth of The People's Daily media coverage, this study investigates social media interactions on family planning policy issues between the state-run news media and individual users in China. Our analysis demonstrates that Weibo postings about the topic by government-run news networks and comments by the general public are affecting each other, but also presenting partially reverse or bottom-up agenda-setting effects. Through latent dirichlet allocation (LDA) modeling, we identified major latent topic sets (women's right to work, family culture/ tradition, law/regulation, and social welfare/wellbeing) and found that Weibo users' main concerns on China's family planning have changed over time. We also found that gender differences affect the topics of commenters.