Cross-platform comparison of framed topics in Twitter and Weibo: machine learning approaches to social media text mining

Abstract

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.

Executives’ ESG cognition and enterprise green innovation: Evidence based on executives’ personal microblogs

“…The two share many similarities, such as a large number of users, a huge amount of user-generated content, continuous and rapid growth, and the same content distribution model and core functions. The nature of social media data, which stores rich textual data about user interactions, can help us understand what users are thinking about a topic or event, enabling systematic analysis of the structure or patterns of activity among individuals or groups ( Yang et al, 2021 ). Research in psychology has also found strong support for the usefulness and validity of integrative language analysis.…”

Comunidades de personas usuarias de Instagram y Twitter de las plataformas audiovisuales online destinadas a la juventud: Playz, MTMAD y Flooxer

“…Mediante este proceso, se han excluido comunidades cuyas descripciones son demasiado genéricas ("soy", "amo", "love" o "like"); o bien que responden únicamente a un criterio geográfico. Diferentes trabajos han señalado el valor de estas técnicas para caracterizar las comunidades de usuarios de las redes, así como para comparar las interacciones entre ellas (Yang et al, 2021).…”

Public Employee Use of Social Media at Work: Competency, Collaboration, and Communication of Workplace Policy

“…Policies on employee social media usage tend to vary across organizations, sectors, and countries (Jacobson & Tufts, 2013). Most private sector organizations create their own social media policy or guidelines and are generally able to dismiss their workers from employment because of what an employee has written on social media posts (Schmidt & O’Connor, 2015; Yang et al, 2021). However, public sector social media policies are distinctive; some may require that a series of legislations be passed to implement social media-related workplace rules.…”