{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:17:40Z","timestamp":1758043060392,"version":"3.44.0"},"reference-count":82,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"crossref","award":["DP220103717"],"award-info":[{"award-number":["DP220103717"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["62072257"],"award-info":[{"award-number":["62072257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>\n            In social networks, echo chambers form when users primarily encounter information that reinforces their existing views with limited exposure to different perspectives. This self-reinforcing isolation worsens societal issues such as division and declining public discourse. Traditional approaches attempt to mitigate echo chambers by analyzing observable interaction patterns to identify their formative mechanisms. However, they overlook unobserved implicit factors, called hidden confounders in causal inference, that significantly influence content exposure and user behaviors despite not being directly captured in the data. To address this, we propose\n            <jats:bold>Causal Echo Diffusion Attenuator (CEDA)<\/jats:bold>\n            , a novel framework that integrates causal learning with sequential recommendations to detect and adjust for hidden confounders in social networks. Generally, CEDA comprises four key components: (1)\n            <jats:italic toggle=\"yes\">User Dual Modelling<\/jats:italic>\n            builds comprehensive user embeddings by combining users\u2019 attributes and structural information to fully capture behavior patterns. (2)\n            <jats:italic toggle=\"yes\">Causal Transformer<\/jats:italic>\n            then estimates residual embeddings that account for hidden confounders, incorporating them into the Transformer as causal adjustments for unbiased user embeddings. (3)\n            <jats:italic toggle=\"yes\">Social Diffusion Predictor<\/jats:italic>\n            uses unbiased user embeddings to jointly optimize diffusion prediction accuracy and information diversity. (4)\n            <jats:italic toggle=\"yes\">Targeted Interventions<\/jats:italic>\n            strategically reshapes information flows to disrupt echo chambers based on the generated prediction and diversity insights. Extensive experiments demonstrate CEDA\u2019s superior performance in both predicting information diffusion patterns and mitigating echo chambers.\n          <\/jats:p>","DOI":"10.1145\/3757738","type":"journal-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T15:18:42Z","timestamp":1754061522000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Breaking the Loop: Causal Learning to Mitigate Echo Chambers in Social Networks"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6376-9667","authenticated-orcid":false,"given":"Dianer","family":"Yu","sequence":"first","affiliation":[{"name":"University of Technology Sydney, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8308-9551","authenticated-orcid":false,"given":"Qian","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering Computing and Mathematical Sciences, Curtin University, Perth, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2440-714X","authenticated-orcid":false,"given":"Huan","family":"Huo","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4493-6663","authenticated-orcid":false,"given":"Guandong","family":"Xu","sequence":"additional","affiliation":[{"name":"Centre for Learning, Teaching &amp; Technology, The Education University of Hong Kong, Hong Kong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2180861.2180866"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3625007.3627731"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1561\/104.00000036"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1804840115"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560694"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2452376.2452451"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615245"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341261"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3045812"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2023301118"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v16i1.19275"},{"key":"e_1_3_2_13_2","unstructured":"Jean-Baptiste Cordonnier Andreas Loukas and Martin Jaggi. 2020. Multi-head attention: Collaborate instead of concatenate. arXiv:2006.16362. Retrieved from https:\/\/arxiv.org\/abs\/2006.16362"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539240"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.64.025101"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1080\/1369118X.2018.1428656"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1287\/isre.1120.0461"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-33370-1"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1083-6101.2009.01440.x"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401431"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1111\/rssa.12276"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186130"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.05.044"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3610639"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3559757"},{"key":"e_1_3_2_28_2","unstructured":"B. Hidasi. 2015. Session-based recommendations with recurrent neural networks. arXiv:1511.06939. Retrieved from https:\/\/arxiv.org\/abs\/1511.06939"},{"key":"e_1_3_2_29_2","first-page":"1","article-title":"Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not","volume":"2022","author":"Hodson Timothy O.","year":"2022","unstructured":"Timothy O. Hodson. 2022. Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not. Geoscientific Model Development Discussions 2022 (2022), 1\u201310.","journal-title":"Geoscientific Model Development Discussions"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507226"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3479859"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-022-09351-w"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/joc\/jqac009"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.4014\/jmb.1709.09027"},{"key":"e_1_3_2_35_2","unstructured":"Diederik P. Kingma. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_36_2","article-title":"Removing hidden confounding in recommendation: A unified multi-task learning approach","volume":"36","author":"Li Haoxuan","year":"2024","unstructured":"Haoxuan Li, Kunhan Wu, Chunyuan Zheng, Yanghao Xiao, Hao Wang, Zhi Geng, Fuli Feng, Xiangnan He, and Peng Wu. 2024. Removing hidden confounding in recommendation: A unified multi-task learning approach. Advances in Neural Information Processing Systems, Vol. 36.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132926"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599519"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01193"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3533725"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2014.93"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219950"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108584"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2435897"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-017-0527-9"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/AERO50100.2021.9438286"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557253"},{"key":"e_1_3_2_48_2","first-page":"419","volume-title":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"7","author":"Munson Sean","year":"2013","unstructured":"Sean Munson, Stephanie Lee, and Paul Resnick. 2013. Encouraging reading of diverse political viewpoints with a browser widget. In Proceedings of the International AAAI Conference on Web and Social Media, Vol. 7, 419\u2013428."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0601602103"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2568012"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.2202\/1557-4679.1203"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0197-y"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959149"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401111"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117275"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.4308"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.75.027105"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42001-020-00084-7"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA49011.2020.00096"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.25300\/MISQ\/2018\/14558"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-008045405-4.00133-6"},{"key":"e_1_3_2_63_2","doi-asserted-by":"crossref","DOI":"10.12840\/ISSN.2255-4165.028","article-title":"Echo chambers on social media: A systematic review of the literature","volume":"9","author":"Terren Ludovic","year":"2021","unstructured":"Ludovic Terren and Rosa Borge-Bravo. 2021. Echo chambers on social media: A systematic review of the literature. Review of Communication Research 9 (2021), 1\u201339.","journal-title":"Review of Communication Research"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474270"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1509\/jmkr.47.4.643"},{"key":"e_1_3_2_66_2","first-page":"707","volume-title":"Conference on Causal Learning and Reasoning","author":"Van Diepen Mirthe Maria","year":"2023","unstructured":"Mirthe Maria Van Diepen, Ioan Gabriel Bucur, Tom Heskes, and Tom Claassen. 2023. Beyond the Markov equivalence class: Extending causal discovery under latent confounding. In Proceedings of the Conference on Causal Learning and Reasoning. PMLR, 707\u2013725."},{"key":"e_1_3_2_67_2","first-page":"74","volume-title":"International Conference on Complex Networks and Their Applications","author":"Vendeville Antoine","year":"2022","unstructured":"Antoine Vendeville, Anastasios Giovanidis, Effrosyni Papanastasiou, and Benjamin Guedj. 2022. Opening up echo chambers via optimal content recommendation. In Proceedings of the International Conference on Complex Networks and Their Applications. Springer, 74\u201385."},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412258"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/2700496"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298988"},{"key":"e_1_3_2_71_2","first-page":"5511","article-title":"Reason generation for point of interest recommendation via a hierarchical attention-based transformer model","author":"Wu Yuxia","year":"2023","unstructured":"Yuxia Wu, Guoshuai Zhao, Mingdi Li, Zhuocheng Zhang, and Xueming Qian. 2023. Reason generation for point of interest recommendation via a hierarchical attention-based transformer model. IEEE Transactions on Multimedia 26 (2023), 5511\u20135522.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_72_2","unstructured":"Guandong Xu Tri Dung Duong Qian Li Shaowu Liu and Xianzhi Wang. 2020. Causality learning: A new perspective for interpretable machine learning. arXiv:2006.16789. Retrieved from https:\/\/arxiv.org\/abs\/2006.16789"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC50000.2020.9219587"},{"key":"e_1_3_2_74_2","article-title":"Understanding and improving layer normalization","volume":"32","author":"Xu Jingjing","year":"2019","unstructured":"Jingjing Xu, Xu Sun, Zhiyuan Zhang, Guangxiang Zhao, and Junyang Lin. 2019. Understanding and improving layer normalization. Advances in Neural Information Processing Systems, Vol. 32.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557300"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2015.2436396"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671807"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3444944"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614803"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/2556613"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412163"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3073064"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060754"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T01:04:16Z","timestamp":1757639056000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"references-count":82,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3757738"],"URL":"https:\/\/doi.org\/10.1145\/3757738","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"type":"print","value":"1046-8188"},{"type":"electronic","value":"1558-2868"}],"subject":[],"published":{"date-parts":[[2025,9,11]]},"assertion":[{"value":"2024-12-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}