Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2026 Feb 23;21(2):e0342677.
doi: 10.1371/journal.pone.0342677. eCollection 2026.

Incorporating topical stance into signed bipartite networks for user retweet prediction

Lixia Li  1 , Ziqing Chen  1 , Haoran Ye  2 , Yixuan Zhang  2
Affiliations

Incorporating topical stance into signed bipartite networks for user retweet prediction

Lixia Li et al. PLoS One. .

Abstract

Social networks accelerate information dissemination, and retweet behavior is an important way of user interaction. User retweet prediction analyzes user characteristics to predict retweet behavior and emotional polarity, which can help platforms understand user emotional tendencies and can be applied to scenarios such as public opinion analysis. However,most existing studies on tree like propagation chains focus on link existence and rarely combine positive negative polarity with topic semantics. This paper constructs a signed bipartite network using user and topic nodes, proposes a Topic Node weighting-based Topical Stance Representation (TNTSR) method, and develops a Topic Stance-integrated Graph Attention Neural Network (TSGAT) for retweet prediction. Experiments on social platform datasets show that both methods outperform benchmarks like SGCN in predicting retweet behavior and polarity. This research effectively leverages topic stance and network structure, enhancing the accuracy of user retweet prediction.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Voting network for US supreme court justices.
Fig 2
Fig 2. The triangular structure of symbolic networks.
Fig 3
Fig 3. The butterfly structure of binary symbolic networks.
Fig 4
Fig 4. US presidential election.
A: User topic network. B: The butterfly structure of social networks. The political caricatures were generated by the authors using Google Gemini AI. All other elements were created by the authors.
Fig 5
Fig 5. Overall framework of topical stance representation method based on topic node weighting.
The political caricatures contained within this figure were generated by the authors using Google Gemini AI. All other elements were created by the authors.
Fig 6
Fig 6. Overall framework of graph attention neural network user retweet prediction method that integrates topical stance.
Fig 7
Fig 7. Classification of positive and negative neighbor sets.
Fig 8
Fig 8. Node neighbor information aggregation mechanism.
See this image and copyright information in PMC

References

    1. Pouyanfar S, Sadiq S, Yan Y, Tian H, Tao Y, Reyes MP. A survey on deep learning: algorithms, techniques, and applications. ACM Computing Surveys. 2018;51(5):1–36.
    1. Huang X, Li J, Yuan Y. Link prediction in dynamic social networks combining entropy, causality, and a graph convolutional network model. Entropy (Basel). 2024;26(6):477. doi: 10.3390/e26060477 - DOI - PMC - PubMed
    1. Xiao H-B, Hu F, Li P-Y, Song Y-R, Zhang Z-K. Information propagation in hypergraph-based social networks. Entropy (Basel). 2024;26(11):957. doi: 10.3390/e26110957 - DOI - PMC - PubMed
    1. Qu S, Xu H, Fu L, Long H, Wang X, Chen G, et al. Tracing truth and rumor diffusions over mobile social networks: who are the initiators?. IEEE Trans on Mobile Comput. 2023;22(4):2473–90. doi: 10.1109/tmc.2021.3119362 - DOI
    1. Li H, Wan H, Chen Y, Ye D, Gel Y, Jiang H. TMetaNet: topological meta-learning framework for dynamic link prediction. arXiv preprint 2025. https://arxiv.org/abs/2506.00453

LinkOut - more resources