{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:04:11Z","timestamp":1770228251984,"version":"3.49.0"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"crossref"}]},{"name":"AI Singapore Programme","award":["AISG2-RP-2021-020"],"award-info":[{"award-number":["AISG2-RP-2021-020"]}]},{"name":"Independent Research Fund Denmark","award":["9041-00382B"],"award-info":[{"award-number":["9041-00382B"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2024,7,31]]},"abstract":"<jats:p>\n            How can we adapt the composition of a post over a series of rounds to make it more appealing in a social network? Techniques that progressively learn how to make a\n            <jats:italic>fixed<\/jats:italic>\n            post more influential over rounds have been studied in the context of the\n            <jats:italic>Influence Maximization<\/jats:italic>\n            (IM) problem, which seeks a set of\n            <jats:italic>seed users<\/jats:italic>\n            that maximize a post\u2019s influence. However, there is no work on progressively learning how a post\u2019s\n            <jats:italic>features<\/jats:italic>\n            affect its influence. In this article, we propose and study the problem of\n            <jats:italic>Adaptive Content-Aware Influence Maximization<\/jats:italic>\n            (ACAIM), which calls to find\n            <jats:italic>k<\/jats:italic>\n            features to form a post in each round so as to maximize the cumulative influence of those posts over all rounds. We solve ACAIM by applying, for the first time, an\n            <jats:italic>Online Learning to Rank<\/jats:italic>\n            (OLR) framework for IM purposes. We introduce the CATRID\n            <jats:italic>propagation model<\/jats:italic>\n            , which expresses how posts disseminate in a social network using click probabilities and post visibility criteria and develop a\n            <jats:italic>simulator<\/jats:italic>\n            that runs CATRID via a training-testing scheme based on real posts of the VK social network, so as to realistically represent the learning environment. We deploy three\n            <jats:italic>learners<\/jats:italic>\n            that solve ACAIM in an online (real-time) manner. We experimentally prove the practical suitability of our solutions via exhaustive experiments on multiple brands (operating as different\n            <jats:italic>case studies<\/jats:italic>\n            ) and several VK datasets; the best learner is evaluated on 45 separate\n            <jats:italic>case studies<\/jats:italic>\n            yielding convincing results.\n          <\/jats:p>","DOI":"10.1145\/3651987","type":"journal-article","created":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T09:19:44Z","timestamp":1709889584000},"page":"1-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Adaptive Content-Aware Influence Maximization via Online Learning to Rank"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1725-1282","authenticated-orcid":false,"given":"Konstantinos","family":"Theocharidis","sequence":"first","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0509-9129","authenticated-orcid":false,"given":"Panagiotis","family":"Karras","sequence":"additional","affiliation":[{"name":"Aarhus University, Aarhus, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0784-8402","authenticated-orcid":false,"given":"Manolis","family":"Terrovitis","sequence":"additional","affiliation":[{"name":"Athena Research Center, Athens, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3465-8292","authenticated-orcid":false,"given":"Spiros","family":"Skiadopoulos","sequence":"additional","affiliation":[{"name":"University of the Peloponnese, Tripoli, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8245-8677","authenticated-orcid":false,"given":"Hady W.","family":"Lauw","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1110.1421"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035924"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.7"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0646-6"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.14778\/2735703.2735706"},{"key":"e_1_3_4_7_2","first-page":"151","volume-title":"ICML","author":"Chen Wei","year":"2013","unstructured":"Wei Chen, Yajun Wang, and Yang Yuan. 2013. Combinatorial multi-armed bandit: General framework, results and applications. In ICML. 151\u2013159."},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946695"},{"key":"e_1_3_4_9_2","first-page":"160","volume-title":"ICML","author":"Chen Yuxin","year":"2013","unstructured":"Yuxin Chen and Andreas Krause. 2013. Near-optimal batch mode active learning and adaptive submodular optimization. In ICML. 160\u2013168."},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02294-4"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2745844.2745852"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/1341531.1341545"},{"issue":"5","key":"e_1_3_4_13_2","first-page":"23","article-title":"LEMON - an open source C++ graph template library","volume":"264","author":"Dezs\u0151 Bal\u00e1zs","year":"2011","unstructured":"Bal\u00e1zs Dezs\u0151, Alp\u00e1r J\u00fcttner, and P\u00e9ter Kov\u00e1cs. 2011. LEMON - an open source C++ graph template library. ENTCS 264, 5 (2011), 23\u201345.","journal-title":"ENTCS"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/2208436.2208448"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.14778\/2047485.2047492"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24027-5_7"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741127"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-020-00615-8"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080788"},{"key":"e_1_3_4_20_2","first-page":"1215","volume-title":"ICML","author":"Katariya Sumeet","year":"2016","unstructured":"Sumeet Katariya, Branislav Kveton, Csaba Szepesv\u00e1ri, and Zheng Wen. 2016. DCM bandits: Learning to rank with multiple clicks. In ICML. 1215\u20131224."},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956769"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411886"},{"key":"e_1_3_4_23_2","first-page":"767","volume-title":"ICML","author":"Kveton Branislav","year":"2015","unstructured":"Branislav Kveton, Csaba Szepesv\u00e1ri, Zheng Wen, and Azin Ashkan. 2015. Cascading bandits: Learning to rank in the cascade model. In ICML. 767\u2013776."},{"key":"e_1_3_4_24_2","first-page":"1450","volume-title":"NeurIPS","author":"Kveton Branislav","year":"2015","unstructured":"Branislav Kveton, Zheng Wen, Azin Ashkan, and Csaba Szepesv\u00e1ri. 2015. Combinatorial cascading bandits. In NeurIPS. 1450\u20131458."},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3274670"},{"key":"e_1_3_4_26_2","first-page":"1605","volume-title":"NeurIPS","author":"Lagr\u00e9e Paul","year":"2016","unstructured":"Paul Lagr\u00e9e, Claire Vernade, and Olivier Capp\u00e9. 2016. Multiple-play bandits in the position-based model. In NeurIPS. 1605\u20131613."},{"key":"e_1_3_4_27_2","first-page":"3949","volume-title":"NeurIPS","author":"Lattimore Tor","year":"2018","unstructured":"Tor Lattimore, Branislav Kveton, Shuai Li, and Csaba Szepesv\u00e1ri. 2018. TopRank: A practical algorithm for online stochastic ranking. In NeurIPS. 3949\u20133958."},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783271"},{"key":"e_1_3_4_29_2","first-page":"3856","volume-title":"ICML","author":"Li Shuai","year":"2019","unstructured":"Shuai Li, Tor Lattimore, and Csaba Szepesv\u00e1ri. 2019. Online learning to rank with features. In ICML. 3856\u20133865."},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2023.113888"},{"key":"e_1_3_4_31_2","first-page":"1245","volume-title":"ICML","author":"Li Shuai","year":"2016","unstructured":"Shuai Li, Baoxiang Wang, Shengyu Zhang, and Wei Chen. 2016. Contextual combinatorial cascading bandits. In ICML. 1245\u20131253."},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807843"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.14778\/2794367.2794376"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242643"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2013.56"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220101"},{"key":"e_1_3_4_37_2","first-page":"3530","volume-title":"ICML","author":"Vaswani Sharan","year":"2017","unstructured":"Sharan Vaswani, Branislav Kveton, Zheng Wen, Mohammad Ghavamzadeh, Laks V.S. Lakshmanan, and Mark Schmidt. 2017. Model-independent online learning for influence maximization. In ICML. 3530\u20133539."},{"key":"e_1_3_4_38_2","unstructured":"Sharan Vaswani Laks. V. S. Lakshmanan and Mark Schmidt. 2016. Influence Maximization with Bandits. https:\/\/arxiv.org\/abs\/1503.00024v4"},{"key":"e_1_3_4_39_2","first-page":"1","volume-title":"NeurIPS","author":"Wen Zheng","year":"2017","unstructured":"Zheng Wen, Branislav Kveton, Michal Valko, and Sharan Vaswani. 2017. Online influence maximization under independent cascade model with semi-bandit feedback. In NeurIPS. 1\u201324."},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330874"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103161"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0127434"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/546"},{"key":"e_1_3_4_44_2","first-page":"4199","volume-title":"ICML","author":"Zoghi Masrour","year":"2017","unstructured":"Masrour Zoghi, Tomas Tunys, Mohammad Ghavamzadeh, Branislav Kveton, Csaba Szepesv\u00e1ri, and Zheng Wen. 2017. Online learning to rank in stochastic click models. In ICML. 4199\u20134208."},{"key":"e_1_3_4_45_2","first-page":"835","volume-title":"UAI","author":"Zong Shi","year":"2016","unstructured":"Shi Zong, Hao Ni, Kenny Sung, Nan Rosemary Ke, Zheng Wen, and Branislav Kveton. 2016. Cascading bandits for large-scale recommendation problems. In UAI. 835\u2013844."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651987","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3651987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:13Z","timestamp":1750268953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":44,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,7,31]]}},"alternative-id":["10.1145\/3651987"],"URL":"https:\/\/doi.org\/10.1145\/3651987","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2023-06-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}