Abstract
With the exponential growth of social media platforms, retweet behavior has become a crucial factor in various social network applications like message diffusion, business intelligence, and E-commerce recommendations. The primary objective of this paper is to predict whether a user will retweet a tweet posted by followees. However, the existing prediction methods cannot model the complex interaction between users. Moreover, some complex and implicit features (e.g. content semantic and structural information) are difficult to be represented and fused reasonably and comprehensively. To address the above issues, we propose a novel framework named RLGAT by using Representation Learning and Graph Attention Networks (GATs) for retweet prediction. RLGAT combines content, structure and social attributes to predict retweet behavior. XLNet-CNN and E-SDNE are employed to generate content and structural representations, respectively. Based on the extracted features of content, structure and social attributes, the AE-GATs model for prediction can further incorporate the correlation of nodes into the generation of node representations. The two real-world datasets are extracted from Sina Microblog and Twitter. The results demonstrate the effectiveness of XLNet-CNN, E-SDNE, AE-GATs, and RLGAT. Notably, RLGAT surpasses state-of-the-art methods, achieving an F1 score of 0.8078 and 0.8017 on Sina and Twitter, respectively. RLGAT is not only effective in predicting user’s retweet behavior, but also beneficial for predicting information diffusion.
Similar content being viewed by others
Data availability
The data of this paper is available on reasonable request.
References
Ortiz-Ospina E, Roser M (2023) The rise of social media. Our world in data. https://ourworldindata.org/rise-of-social-media
Jain PK, Patel A, Kumari S et al (2022) Predicting airline customers’ recommendations using qualitative and quantitative contents of online reviews. Multimed Tools App 81(5):6979–6994
Jain PK, Pamula R, Srivastava G (2021) A systematic literature review on machine learning applications for consumer sentiment analysis using online reviews. Computer Sci Rev 41:100413
Lahuerta-Otero E, Cordero-Gutiérrez R, De la Prieta-Pintado F (2018) Retweet or like? That is the question. Online Inf Rev 42(5):562–578
Lymperopoulos IN (2021) RC-Tweet: modeling and predicting the popularity of tweets through the dynamics of a capacitor. Expert Syst Appl 163:113785
Wang L, Hu K, Zhang Y et al (2019) Factor graph model based user profile matching across social networks. IEEE Access 7:152429–152442
Shaoqing W, Cuiping L, Zheng W et al (2019) Prediction of retweet behavior based on multiple trust relationships. J Tsinghua Univ (Sci Technol) 59(4):270–275
Babić K, Petrović M, Beliga S et al (2021) Prediction of COVID-19 related information spreading on Twitter. 2021 44th International Convention on Information, Communication and Electronic Technology (MIPRO). IEEE, Opatija, Croatia, pp 395–399
Tsugawa S (2019) Empirical analysis of the relation between community structure and cascading retweet diffusion. In: Proceedings of the International AAAI Conference on Web and Social Media, vol 13. AAAI, Münich, Germany, pp 493–504
Yan Y, Toriumi F, Sugawara T (2021) Understanding how retweets influence the behaviors of social networking service users via agent-based simulation. Comput Social Netw 8(1):1–21
Lei K, Qin M, Bai B et al (2019) GCN-GAN: A non-linear temporal link prediction model for weighted dynamic networks. IEEE INFOCOM 2019-IEEE Conference on Computer Communications. IEEE, Paris, France, pp 388–396
Malekzadeh M, Hajibabaee P, Heidari M et al (2021) Review of graph neural network in text classification. 2021 IEEE 12th annual ubiquitous computing, electronics & mobile communication conference (UEMCON). IEEE, New York, USA, pp 0084–0091
Saxena N, Sinha A, Bansal T et al (2023) A statistical approach for reducing misinformation propagation on twitter social media. Inf Process Manage 60(4):103360
Yao L, Mao C, Luo Y (2019) Graph convolutional networks for text classification. In: Proc AAAI Conf Artif Intell. AAAI, Honolulu, Hawaii, 33(01):7370–7377
Huang S, Yu W (2023) Cascade Prediction with Recurrent Neural Networks and Diffusion Depth Distributions[C]. 2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE). IEEE, Guangzhou, China, pp 70–77
Xiao Y, Huang Z, Li Q et al (2023) Diffusion Pixelation: A Game Diffusion Model of Rumor & Anti-Rumor Inspired by Image Restoration. IEEE Trans Knowl Data Eng 35(5):4682–4694
Cai T, Li J, Mian A et al (2020) Target-aware holistic influence maximization in spatial social networks. IEEE Trans Knowl Data Eng 34(4):1993–2007
Sharma S, Gupta V (2022) Role of twitter user profile features in retweet prediction for big data streams. Multimed Tools App 81(19):27309–27338
Firdaus SN, Ding C, Sadeghian A (2021) Retweet prediction based on topic, emotion and personality. Online Social Networks Media 25:100165
Zhang Q, Gong Y, Guo Y et al (2015) Retweet behavior prediction using hierarchical dirichlet process. In Proc AAAI Conf Artif Intell 29(1):1–7
Dai T, Xiao Y, Liang X et al (2022) ICS-SVM: A user retweet prediction method for hot topics based on improved SVM. Digital Commun Netw 8(2):186–193
Firdaus SN, Ding C, Sadeghian A (2019) Topic specific emotion detection for retweet prediction. Int J Mach Learn Cybern 10:2071–2083
Wang S, Li C, Wang Z et al (2020) BPF++: A Unified Factorization model for predicting retweet behaviors. Inf Sci 515:218–232
Daga I, Gupta A, Vardhan R et al (2020) Prediction of likes and retweets using text information retrieval. Procedia Comput Sci 168:123–128
Zhang Q, Gong Y, Wu J et al (2016) Retweet prediction with attention-based deep neural network. In: Proceedings of the 25th ACM Int Conf Inf Knowledge Manag. ACM, Indianapolis, USA, pp 75–84
Wang L, Zhang Y, Yuan J et al (2022) FEBDNN: fusion embedding-based deep neural network for user retweeting behavior prediction on social networks. Neural Comput App 34(16):13219–13235
Ma R, Hu X, Zhang Q, et al. (2020) Hot topic-aware retweet prediction with masked self-attentive model. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval. 525–534
Li Q, Yang J, Dai T et al (2023) A predictive model based on user awareness and multi-type rumors forwarding dynamics. Inf Sci 619:795–816
Wang J, Yang Y (2022) Tweet retweet prediction based on deep multitask learning. Neural Process Lett 54(1):523–536
Khan PI, Razzak I, Dengel A et al (2021) Understanding information spreading mechanisms during COVID-19 pandemic by analyzing the impact of tweet text and user features for retweet prediction. arXiv preprint arXiv:2106.07344. https://doi.org/10.48550/arXiv.2106.07344
Liu Y, Zhao J, Xiao Y (2018) C-RBFNN: A user retweet behavior prediction method for hotspot topics based on improved RBF neural network. Neurocomputing 275:733–746
Amitani R, Matsumoto K, Yoshida M et al (2021) Prediction of Number of Likes and Retweets based on the Features of Tweet Text and Images. In: 2021 5th International Conference on Natural Language Processing and Information Retrieval (NLPIR). ACM, New York, United States, pp 94–101
Yin H, Yang S, Song X et al (2021) Deep fusion of multimodal features for social media retweet time prediction. World Wide Web 24(4):1027–1044
Yu L, Xu X, Trajcevski G et al (2022) Transformer-enhanced Hawkes process with decoupling training for information cascade prediction. Knowl-Based Syst 255:109740
Xiang T, Li Q, Li W et al (2023) A rumor heat prediction model based on rumor and anti-rumor multiple messages and knowledge representation. Inf Process Manage 60(3):103337
Li Z, Tang J, Mei T (2018) Deep collaborative embedding for social image understanding. IEEE Trans Pattern Anal Mach Intell 41(9):2070–2083
Li Z, Tang J (2016) Weakly supervised deep matrix factorization for social image understanding. IEEE Trans Image Process 26(1):276–288
Wang D, Cui P, Zhu W (2016) Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, San Francisco, CA, pp 1225–1234
Joshi A, Fidalgo E, Alegre E et al (2022) RankSum-An unsupervised extractive text summarization based on rank fusion. Expert Syst Appl 200:116846
Kim D, Seo D, Cho S et al (2019) Multi-co-training for document classification using various document representations: TF-IDF, LDA, and Doc2Vec. Inf Sci 477:15–29
Yang Z, Dai Z, Yang Y et al (2019) Xlnet: Generalized autoregressive pretraining for language understanding. 33rd Conference on Neural Information Processing Systems. MIT Press, Vancouver, Canada, pp 1–11
Jain L, Katarya R, Sachdeva S (2023) Opinion Leaders for Information Diffusion Using Graph Neural Network in Online Social Networks. ACM Trans Web 17(2):1–37
Wu H, Hu Z, Jia J et al (2020) Mining Unfollow Behavior in Large-Scale Online Social Networks via Spatial-Temporal Interaction. In Proc AAAI Conf Artif Intell 34(01):254–261
Wang L, Zhang Y, Hu K (2022) FEUI: Fusion Embedding for User Identification across social networks. Appl Intell 52(7):8209–8225
Zhang J, Tang J, Li J et al (2015) Who influenced you? predicting retweet via social influence locality. ACM Trans Knowledge Discov from Data (TKDD) 9(3):1–26
Guo H, Yang L, Liu Z (2021) UserRBPM: User Retweet Behavior Prediction with Graph Representation Learning. Wireless Commun Mobile Comput 2021:4431416
Zhang Y, Shen J, Zhang R et al (2023) Network representation learning via improved random walk with restart. Knowledge-Based Syst 263:110255
Zhou X, Liang W, Luo Z et al (2021) Periodic-aware intelligent prediction model for information diffusion in social networks. IEEE Trans Netw Sci Eng 8(2):894–904
Yuan C, Li J, Zhou W et al (2021) DyHGCN: A dynamic heterogeneous graph convolutional network to learn users’ dynamic preferences for information diffusion prediction. Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2020. Springer, Ghent, Belgium, pp 347–363
Pan L, Xiong Y, Li B et al (2023) Feature attenuation reinforced recurrent neural network for diffusion prediction. Appl Intell 53(2):1855–1869
Turenne N (2018) The rumour spectrum[J]. PLoS One 13(1):e0189080
Cheng J, Adamic L, Dow PA et al (2014) Can cascades be predicted? In: Proceedings of the 23rd international conference on World Wide Web. ACM, Seoul, Republic of Korea, pp 925–936
Acknowledgements
This study is supported by Zhejiang Provincial High-Education Teaching Reform Project under Grant No.jg20220770, Medical and Health Technology Plan of Zhejiang Province (No. 2022507615), China Knowledge Centre for Engineering Sciences and Technology(CKCEST), Natural Science Foundation of Ningbo (No. 2023J297).
Authors contribution statement
Author information
Authors and Affiliations
Contributions
Lidong Wang: modeling, coding, and writing. Yin Zhang: Visualization, Investigation. Jie Yuan: background research, related works, and writing review. Shihua Cao: Reviewing and Editing, Writing, Data curation. Bin Zhou: Reviewing.
Corresponding author
Ethics declarations
Ethical and informed consent for data used
Not applicable.
Competing interests
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, L., Zhang, Y., Yuan, J. et al. RLGAT: Retweet prediction in social networks using representation learning and GATs. Multimed Tools Appl 83, 40909–40938 (2024). https://doi.org/10.1007/s11042-023-16902-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16902-9