{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:14:05Z","timestamp":1772554445309,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012352","name":"Universit\u00e0 degli Studi di Milano","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100012352","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Link prediction in Online Social Networks\u2014OSNs\u2014has been the focus of numerous studies in the machine learning community. A successful machine learning-based solution for this task needs to (i) leverage global and local properties of the graph structure surrounding links; (ii) leverage the content produced by OSN users; and (iii) allow their representations to change over time, as thousands of new links between users and new content like textual posts, comments, images and videos are created\/uploaded every month. Current works have successfully leveraged the structural information but only a few have also taken into account the textual content and\/or the dynamicity of network structure and node attributes. In this paper, we propose a methodology based on temporal graph neural networks to handle the challenges described above. To understand the impact of textual content on this task, we provide a novel pipeline to include textual information alongside the structural one with the usage of BERT language models, dense preprocessing layers, and an effective post-processing decoder. We conducted the evaluation on a novel dataset gathered from an emerging blockchain-based online social network, using a live-update setting that takes into account the evolving nature of data and models. The dataset serves as a useful testing ground for link prediction evaluation because it provides high-resolution temporal information on link creation and textual content, characteristics hard to find in current benchmark datasets. Our results show that temporal graph learning is a promising solution for dynamic link prediction with text. Indeed, combining textual features and dynamic Graph Neural Networks\u2014GNNs\u2014leads to the best performances over time. On average, the textual content can enhance the performance of a dynamic GNN by 3.1% and, as the collection of documents increases in size over time, help even models that do not consider the structural information of the network.<\/jats:p>","DOI":"10.1007\/s10994-023-06475-x","type":"journal-article","created":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T17:02:25Z","timestamp":1701277345000},"page":"2207-2226","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Temporal graph learning for dynamic link prediction with text in online social networks"],"prefix":"10.1007","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4861-455X","authenticated-orcid":false,"given":"Manuel","family":"Dileo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4808-4106","authenticated-orcid":false,"given":"Matteo","family":"Zignani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3779-2809","authenticated-orcid":false,"given":"Sabrina","family":"Gaito","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,29]]},"reference":[{"key":"6475_CR1","doi-asserted-by":"crossref","unstructured":"Ba, C. T., Michienzi, A., Guidi, B., Zignani, M., Ricci, L., & Gaito, S. (2022a). Fork-based user migration in blockchain online social media. In 14th ACM web science conference 2022, (pp. 174\u2013184).","DOI":"10.1145\/3501247.3531597"},{"issue":"6","key":"6475_CR3","doi-asserted-by":"publisher","first-page":"e0267612","DOI":"10.1371\/journal.pone.0267612","volume":"17","author":"CT Ba","year":"2022","unstructured":"Ba, C. T., Zignani, M., & Gaito, S. (2022b). The role of cryptocurrency in the dynamics of blockchain-based social networks: The case of steemit. PloS one, 17(6), e0267612.","journal-title":"PloS one"},{"key":"6475_CR2","doi-asserted-by":"publisher","unstructured":"Barracchia, E., Pio, G., Bifet, A., Gomes, H. M., Pfahringer, B., & Ceci, M. (2022). Lp-robin: Link prediction in dynamic networks exploiting incremental node embedding. Information Sciences 606. https:\/\/doi.org\/10.1016\/j.ins.2022.05.079","DOI":"10.1016\/j.ins.2022.05.079"},{"key":"6475_CR4","doi-asserted-by":"crossref","unstructured":"Bruss, C. B., Khazane, A., Rider, J., Serpe, R. T., Gogoglou, A., & Hines, K. E. (2019). Deeptrax: Embedding graphs of financial transactions. In 2019 18th IEEE international conference on machine learning and applications (ICMLA) (pp. 126\u2013133).","DOI":"10.1109\/ICMLA.2019.00028"},{"key":"6475_CR5","unstructured":"Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. In NIPS 2014 workshop on deep learning, 2014."},{"key":"6475_CR6","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2019). BERT: pre-training of deep bidirectional transformers for language understanding. In J.\u00a0Burstein, C.\u00a0Doran, T.\u00a0Solorio (eds.) Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: Human language technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, (Long and Short Papers), (Vol. 1, pp. 4171\u20134186). Association for Computational Linguistics . https:\/\/doi.org\/10.18653\/v1\/n19-1423.","DOI":"10.18653\/v1\/n19-1423"},{"key":"6475_CR7","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-031-18840-4_16","volume-title":"Discovery science","author":"M Dileo","year":"2022","unstructured":"Dileo, M., Ba, C. T., Zignani, M., & Gaito, S. (2022). Link prediction with text in online social networks: The role of textual content on high-resolution temporal data. In P. Pascal & D. Ienco (Eds.), Discovery science (pp. 212\u2013226). Cham: Springer Nature Switzerland."},{"key":"6475_CR8","unstructured":"Fey, M., & Lenssen, J. E. (2019). Fast graph representation learning with pytorch geometric. arxiv:1903.02428"},{"issue":"1","key":"6475_CR9","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1609\/icwsm.v15i1.18049","volume":"15","author":"K Garimella","year":"2021","unstructured":"Garimella, K., Smith, T., Weiss, R., & West, R. (2021). Political polarization in online news consumption. Proceedings of the International AAAI Conference on Web and Social Media, 15(1), 152\u2013162. https:\/\/doi.org\/10.1609\/icwsm.v15i1.18049","journal-title":"Proceedings of the International AAAI Conference on Web and Social Media"},{"issue":"21","key":"6475_CR10","doi-asserted-by":"publisher","first-page":"9880","DOI":"10.3390\/app11219880","volume":"11","author":"B Guidi","year":"2021","unstructured":"Guidi, B. (2021). An overview of blockchain online social media from the technical point of view. Applied Sciences, 11(21), 9880.","journal-title":"Applied Sciences"},{"key":"6475_CR11","unstructured":"Gupta, S., & Bedathur, S. (2022). A survey on temporal graph representation learning and generative modeling. arxiv:2208.12126"},{"key":"6475_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11857-1","author":"KZ Khanam","year":"2022","unstructured":"Khanam, K. Z., Srivastava, G., & Mago, V. (2022). The homophily principle in social network analysis: A survey. Multimedia Tools and Applications. https:\/\/doi.org\/10.1007\/s11042-021-11857-1","journal-title":"Multimedia Tools and Applications"},{"key":"6475_CR13","unstructured":"Kingma, D.P., & Ba, J. (2015). Adam: A method for stochastic optimization. In: Y.\u00a0Bengio, Y.\u00a0LeCun (eds.) ICLR (Poster). http:\/\/dblp.uni-trier.de\/db\/conf\/iclr\/iclr2015.html#KingmaB14"},{"key":"6475_CR14","unstructured":"Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International conference on learning representations (ICLR)."},{"key":"6475_CR16","doi-asserted-by":"publisher","first-page":"124289","DOI":"10.1016\/j.physa.2020.124289","volume":"553","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Singh, S. S., Singh, K., & Biswas, B. (2020). Link prediction techniques, applications, and performance: A survey. Physica A-statistical Mechanics and Its Applications, 553, 124289.","journal-title":"Physica A-statistical Mechanics and Its Applications"},{"key":"6475_CR15","doi-asserted-by":"crossref","unstructured":"Kumar, S., Hamilton, W. L., Leskovec, J., Jurafsky, D. (2018). Community interaction and conflict on the web. In Proceedings of the 2018 World Wide Web Conference on World Wide Web, (pp. 933\u2013943). International World Wide Web Conferences Steering Committee","DOI":"10.1145\/3178876.3186141"},{"key":"6475_CR17","unstructured":"Li, Y., Yu, R., Shahabi, C., & Liu, Y. (2018). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SJiHXGWAZ"},{"key":"6475_CR18","doi-asserted-by":"publisher","unstructured":"Liben-Nowell, D., & Kleinberg, J. (2003). The link prediction problem for social networks. In Proceedings of the Twelfth International Conference on Information and Knowledge Management, CIKM \u201903, (pp. 556\u2013559). Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/956863.956972.","DOI":"10.1145\/956863.956972"},{"issue":"01","key":"6475_CR20","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1109\/TKDE.2021.3077495","volume":"35","author":"P Liu","year":"2023","unstructured":"Liu, P., Guarrasi, V., & Saryuce, A. (2023). Temporal network motifs: Models, limitations, evaluation. IEEE Transactions on Knowledge & Data Engineering, 35(01), 945\u2013957. https:\/\/doi.org\/10.1109\/TKDE.2021.3077495","journal-title":"IEEE Transactions on Knowledge & Data Engineering"},{"key":"6475_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Q., Tang, S., Zhang, X., Zhao, X., Zhao, B. Y., & Zheng, H. (2016). Network growth and link prediction through an empirical lens. In Proceedings of the 2016 Internet Measurement Conference.","DOI":"10.1145\/2987443.2987452"},{"key":"6475_CR21","unstructured":"Longa, A., Lachi, V., Santin, G., Bianchini, M., Lepri, B., Lio, P., Scarselli, F., & Passerini, A. (2023).Graph neural networks for temporal graphs: State of the art, open challenges, and opportunities. arxiv:2302.01018"},{"key":"6475_CR22","doi-asserted-by":"publisher","unstructured":"Monti, C., Rozza, A., Zappella, G., Zignani, M., Arvidsson, A., & Colleoni, E. (2013). Modelling political disaffection from twitter data. In Proceedings of the second international workshop on issues of sentiment discovery and opinion mining, WISDOM \u201913. Association for Computing Machinery, New York, NY, USA . https:\/\/doi.org\/10.1145\/2502069.2502072.","DOI":"10.1145\/2502069.2502072"},{"issue":"04","key":"6475_CR23","doi-asserted-by":"publisher","first-page":"5363","DOI":"10.1609\/aaai.v34i04.5984","volume":"34","author":"A Pareja","year":"2020","unstructured":"Pareja, A., Domeniconi, G., Chen, J., Ma, T., Suzumura, T., Kanezashi, H., Kaler, T., Schardl, T., & Leiserson, C. (2020). Evolvegcn: Evolving graph convolutional networks for dynamic graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 5363\u20135370. https:\/\/doi.org\/10.1609\/aaai.v34i04.5984","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"6475_CR24","doi-asserted-by":"crossref","unstructured":"Parimi, R., & Caragea, D. (2011). Predicting friendship links in social networks using a topic modeling approach. In PAKDD.","DOI":"10.1007\/978-3-642-20847-8_7"},{"key":"6475_CR25","doi-asserted-by":"publisher","unstructured":"Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), (pp. 3982\u20133992). Association for Computational Linguistics, Hong Kong, China . https:\/\/doi.org\/10.18653\/v1\/D19-1410. https:\/\/aclanthology.org\/D19-1410","DOI":"10.18653\/v1\/D19-1410"},{"key":"6475_CR26","unstructured":"Rossi, E., Chamberlain, B., Frasca, F., Eynard, D., Monti, F., & Bronstein, M. (2020). Temporal graph networks for deep learning on dynamic graphs. In ICML 2020 workshop on graph representation learning."},{"key":"6475_CR27","doi-asserted-by":"publisher","unstructured":"Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. In 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE. https:\/\/doi.org\/10.1109\/cvpr.2015.7298682. https:\/\/doi.org\/10.1109%2Fcvpr.2015.7298682","DOI":"10.1109\/cvpr.2015.7298682"},{"key":"6475_CR28","doi-asserted-by":"crossref","unstructured":"Seo, Y., Defferrard, M., Vandergheynst, P., & Bresson, X. (2018). Structured sequence modeling with graph convolutional recurrent networks. In Neural information processing: 25th international conference, ICONIP 2018, Siem Reap, Cambodia, December 13\u201316, 2018, Proceedings, Part I 25, (pp. 362\u2013373). Springer","DOI":"10.1007\/978-3-030-04167-0_33"},{"key":"6475_CR29","doi-asserted-by":"publisher","unstructured":"Spillo, G., Musto, C., Polignano, M., Lops, P., de\u00a0Gemmis, M., & Semeraro, G. (2023). Combining graph neural networks and sentence encoders for knowledge-aware recommendations. In Proceedings of the 31st ACM conference on user modeling, adaptation and personalization, UMAP \u201923, (pp. 1\u201312). Association for Computing Machinery, New York, NY, USA . https:\/\/doi.org\/10.1145\/3565472.3592965.","DOI":"10.1145\/3565472.3592965"},{"issue":"1","key":"6475_CR30","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/s13278-021-00779-3","volume":"11","author":"G Villa","year":"2021","unstructured":"Villa, G., Pasi, G., & Viviani, M. (2021). Echo chamber detection and analysis: A topology- and content-based approach in the COVID-19 scenario. Social Network Analysis and Mining, 11(1), 78.","journal-title":"Social Network Analysis and Mining"},{"key":"6475_CR31","unstructured":"Wang, Y., Hooi, B., Liu, Y., Zhao, T., Guo, Z., & Shah, N. (2022). Flashlight: Scalable link prediction with effective decoders. arxiv:2209.10100"},{"key":"6475_CR32","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.eswa.2018.04.034","volume":"108","author":"Z Wang","year":"2018","unstructured":"Wang, Z., Liang, J., & Li, R. (2018). Exploiting user-to-user topic inclusion degree for link prediction in social-information networks. Expert Systems with Applications, 108, 143\u2013158.","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"6475_CR33","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/tnnls.2020.2978386","volume":"32","author":"Z Wu","year":"2021","unstructured":"Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021). A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 4\u201324. https:\/\/doi.org\/10.1109\/tnnls.2020.2978386","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"6475_CR34","doi-asserted-by":"publisher","unstructured":"Xu, S., Yang, C., Shi, C., Fang, Y., Guo, Y., Yang, T., Zhang, L., & Hu, M. (2021). Topic-aware heterogeneous graph neural network for link prediction. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, CIKM \u201921, (pp. 2261\u20132270). Association for Computing Machinery, New York, NY, USA . https:\/\/doi.org\/10.1145\/3459637.3482485.","DOI":"10.1145\/3459637.3482485"},{"issue":"3","key":"6475_CR35","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1007\/s10115-014-0789-0","volume":"45","author":"Y Yang","year":"2014","unstructured":"Yang, Y., Lichtenwalter, R. N., & Chawla, N. V. (2014). Evaluating link prediction methods. Knowledge and Information Systems, 45(3), 751\u2013782. https:\/\/doi.org\/10.1007\/s10115-014-0789-0","journal-title":"Knowledge and Information Systems"},{"key":"6475_CR36","doi-asserted-by":"publisher","unstructured":"You, J., Du, T., & Leskovec, J. (2019). Roland: Graph learning framework for dynamic graphs. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, KDD \u201922, (pp. 2358\u20132366). Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3534678.3539300. https:\/\/doi.org\/10.1145\/3534678.3539300","DOI":"10.1145\/3534678.3539300"},{"key":"6475_CR37","doi-asserted-by":"publisher","unstructured":"You, J., Wang, Y., Pal, A., & Eksombatchai, P., Rosenberg, C., & Leskovec, J. (2019). Hierarchical temporal convolutional networks for dynamic recommender systems. In L.\u00a0Liu, R.W. White, A.\u00a0Mantrach, F.\u00a0Silvestri, J. J. McAuley, R.\u00a0Baeza-Yates, L.\u00a0Zia (eds.) The World Wide Web Conference, WWW 2019, San Francisco, CA, USA, May 13\u201317, 2019, (pp. 2236\u20132246). ACM. https:\/\/doi.org\/10.1145\/3308558.3313747.","DOI":"10.1145\/3308558.3313747"},{"key":"6475_CR38","doi-asserted-by":"crossref","unstructured":"Yu, B., Yin, H., & Zhu, Z. (2018). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In Proceedings of the 27th international joint conference on artificial intelligence, IJCAI\u201918, (pp. 3634\u20133640). AAAI Press","DOI":"10.24963\/ijcai.2018\/505"},{"issue":"9","key":"6475_CR39","doi-asserted-by":"publisher","first-page":"3848","DOI":"10.1109\/tits.2019.2935152","volume":"21","author":"L Zhao","year":"2020","unstructured":"Zhao, L., Song, Y., Zhang, C., Liu, Y., Wang, P., Lin, T., Deng, M., & Li, H. (2020). T-GCN: A temporal graph convolutional network for traffic prediction. IEEE Transactions on Intelligent Transportation Systems, 21(9), 3848\u20133858. https:\/\/doi.org\/10.1109\/tits.2019.2935152","journal-title":"IEEE Transactions on Intelligent Transportation Systems"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06475-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06475-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06475-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T17:15:56Z","timestamp":1711646156000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06475-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,29]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["6475"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06475-x","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,29]]},"assertion":[{"value":"11 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The data collected are publicly available and accessible on the Steem blockchain. We followed well-established ethical procedures for social data and obtained a waiver from the ethics committee at the University of Milan. All data is pseudo-anonymized before usage, it is stored within a secure silo, while the text is not stored in a readable format but in a vector representation.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}