Context is Key(NMF): Modelling Topical Information Dynamics in Chinese Diaspora Media
Ross Deans Kristensen-McLachlan, Rebecca M. M. Hicke, Márton Kardos, Mette Thunø
2024-10-21
Summary
This paper explores how the People's Republic of China (PRC) influences European elections through media aimed at the ethnic Chinese diaspora, using a new method called KeyNMF to analyze the narratives in Chinese media.
What's the problem?
There are concerns that the PRC may interfere with European elections by spreading specific narratives through Chinese diaspora media. Understanding how these narratives are formed and their potential impact is crucial, but analyzing this information on a large scale can be challenging. Traditional methods may not effectively capture the dynamics of how these narratives change over time.
What's the solution?
To address this issue, the authors developed KeyNMF, a new approach to topic modeling that uses advanced techniques to analyze both static and dynamic topics in Chinese media. They applied this method to data from five different news sites during the lead-up to the 2024 European parliamentary elections. By focusing on how topics evolve, they can better understand the PRC's objectives and strategies in influencing public opinion through diaspora media.
Why it matters?
This research is important because it sheds light on how foreign powers might manipulate media to influence elections in other countries. By understanding these tactics, researchers and policymakers can better protect democratic processes and ensure fair elections, which is vital for maintaining trust and integrity in political systems.
Abstract
Does the People's Republic of China (PRC) interfere with European elections through ethnic Chinese diaspora media? This question forms the basis of an ongoing research project exploring how PRC narratives about European elections are represented in Chinese diaspora media, and thus the objectives of PRC news media manipulation. In order to study diaspora media efficiently and at scale, it is necessary to use techniques derived from quantitative text analysis, such as topic modelling. In this paper, we present a pipeline for studying information dynamics in Chinese media. Firstly, we present KeyNMF, a new approach to static and dynamic topic modelling using transformer-based contextual embedding models. We provide benchmark evaluations to demonstrate that our approach is competitive on a number of Chinese datasets and metrics. Secondly, we integrate KeyNMF with existing methods for describing information dynamics in complex systems. We apply this pipeline to data from five news sites, focusing on the period of time leading up to the 2024 European parliamentary elections. Our methods and results demonstrate the effectiveness of KeyNMF for studying information dynamics in Chinese media and lay groundwork for further work addressing the broader research questions.