Domain-based user embedding for competing events on social media
Bibliographic Data
| ID | 7158751 |
|---|---|
| Authors | Wentao Xu (0000-0003-4227-8150, University of Science and Technology of China, corresponding author), Kazutoshi Sasahara (0000-0003-2572-0648) |
| Year | 2026 |
| Volume | 9 |
| Issue | 1 |
| Publication date | 2026-02-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Journal of Computational Social Science (JOURNAL) |
| Journal identifiers | ISSN: 2432-2725 • E-ISSN: 2432-2717 |
| Publisher | Springer Science and Business Media LLC (PUBLISHER) |
| DOI | 10.1007/s42001-025-00439-y |
| OpenAlex | W4417487857 |
| Language | EN |
| References cited | 68 |
Social divide and polarization have become significant societal issues. To understand the mechanisms behind these phenomena, social media analysis offers research opportunities in computational social science, where developing effective user embedding methods is essential for subsequent analysis. Traditionally, researchers have used predefined network-based user features (e.g., network size, degree, and centrality measures). However, because such measures may not capture the complex characteristics of social media users, in our study we developed a method for embedding users based on a URL domain co-occurrence network. This approach effectively represents social media users involved in competing events such as political campaigns and public health crises. We assessed the method’s performance using binary classification tasks and datasets that covered topics associated with the COVID-19 infodemic, such as QAnon, Biden, and Ivermectin, among Twitter users. Our results revealed that user embeddings generated directly from the retweet network and/or based on language performed below expectations, whereas our domain-based embeddings outperformed those methods while reducing computation time. Therefore, domain-based embedding offers an accessible and effective method for characterizing social media users in competing events
Centrality · Embedding · Social media · Social network analysis · Advanced Graph Neural Networks · Complex Network Analysis Techniques · Misinformation and Its Impacts
ArnetMiner
The political blogosphere and the 2004 U.S. election
Line
ForceAtlas2, a Continuous Graph Layout Algorithm for Handy Network Visualization Designed for the Gephi Software
Polarization of the vaccination debate on Facebook
How digital media drive affective polarization through partisan sorting
The Network Data Repository with Interactive Graph Analytics and Visualization
DeepWalk
Want to be Retweeted? Large Scale Analytics on Factors Impacting Retweet in Twitter Network
Deep Contextualized Word Representations
Cognitive–motivational mechanisms of political polarization in social-communicative contexts
Node2vec
Tweet, Tweet, Retweet
Political Discourse on Social Media
Fast unfolding of communities in large networks
Rise and fall of the global conversation and shifting sentiments during the Covid-19 pandemic
Aggressive behaviour of anti-vaxxers and their toxic replies in English and Japanese
How epidemic psychology works on Twitter
Social media construction of sexual deviance in Hong Kong
Social influence and unfollowing accelerate the emergence of echo chambers
The wisdom of polarized crowds
Overperception of moral outrage in online social networks inflates beliefs about intergroup hostility
The unequal landscape of civic opportunity in America
Psychological inoculation strategies to fight climate disinformation across 12 countries
Global evidence of expressed sentiment alterations during the Covid-19 pandemic
Interventions to reduce partisan animosity
The Geometry of Culture
| Citation velocity | historical |
|---|---|
| Highly cited | No |