{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:41:59Z","timestamp":1740123719483,"version":"3.37.3"},"reference-count":96,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,6,4]],"date-time":"2022-06-04T00:00:00Z","timestamp":1654300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,6,4]],"date-time":"2022-06-04T00:00:00Z","timestamp":1654300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["User Model User-Adap Inter"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s11257-022-09331-0","type":"journal-article","created":{"date-parts":[[2022,6,4]],"date-time":"2022-06-04T05:02:20Z","timestamp":1654318940000},"page":"611-648","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Dirichlet\u2013Luce choice model for learning from interactions"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8624-5265","authenticated-orcid":false,"given":"G\u00f6khan","family":"\u00c7apan","sequence":"first","affiliation":[]},{"given":"\u0130lker","family":"G\u00fcndo\u011fdu","sequence":"additional","affiliation":[]},{"given":"Ali Caner","family":"T\u00fcrkmen","sequence":"additional","affiliation":[]},{"given":"Ali Taylan","family":"Cemgil","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,4]]},"reference":[{"key":"9331_CR1","doi-asserted-by":"publisher","unstructured":"Abdollahpouri, H.: Popularity bias in ranking and recommendation. In: The 2019 AAAI\/ACM Conference on AI, Ethics, and Society, pp. 27\u201328 (2019). https:\/\/doi.org\/10.1145\/3306618.3314309","DOI":"10.1145\/3306618.3314309"},{"key":"9331_CR2","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Wang, X., Li, C., Bendersky, M., Najork, M.: Addressing trust bias for unbiased learning-to-rank. In: The World Wide Web Conference, pp. 4\u201314 (2019)","DOI":"10.1145\/3308558.3313697"},{"key":"9331_CR3","unstructured":"Ailon, N., Karnin, Z., Joachims, T.: Reducing dueling bandits to cardinal bandits. In: International Conference on Machine Learning, pp. 856\u2013864 (2014)"},{"issue":"6","key":"9331_CR4","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/3209581","volume":"61","author":"R Baeza-Yates","year":"2018","unstructured":"Baeza-Yates, R.: Bias on the web. Commun. ACM 61(6), 54\u201361 (2018)","journal-title":"Commun. ACM"},{"key":"9331_CR5","doi-asserted-by":"publisher","unstructured":"Baeza-Yates, R.: Bias in search and recommender systems. In: Fourteenth ACM Conference on Recommender Systems, RecSys \u201920, p.\u00a02 (2020). https:\/\/doi.org\/10.1145\/3383313.3418435","DOI":"10.1145\/3383313.3418435"},{"key":"9331_CR6","unstructured":"Balog, M., Tripuraneni, N., Ghahramani, Z., Weller, A.: Lost relatives of the Gumbel trick. In: Proceedings of the 34th International Conference on Machine Learning, ICML\u201917, vol. 70, pp. 371\u2013379 (2017)"},{"key":"9331_CR7","unstructured":"Basilico, J.: Recent trends in personalization: a Netflix perspective. In: ICML 2019 Workshop on Adaptive and Multitask Learning. ICML (2019)"},{"key":"9331_CR8","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"issue":"3\/4","key":"9331_CR9","doi-asserted-by":"publisher","first-page":"324","DOI":"10.2307\/2334029","volume":"39","author":"RA Bradley","year":"1952","unstructured":"Bradley, R.A., Terry, M.E.: Rank analysis of incomplete block designs: I the method of paired comparisons. Biometrika 39(3\/4), 324\u2013345 (1952)","journal-title":"Biometrika"},{"key":"9331_CR10","unstructured":"Busa-Fekete, R., Szorenyi, B., Cheng, W., Weng, P., H\u00fcllermeier, E.: Top-k selection based on adaptive sampling of noisy preferences. In: International Conference on Machine Learning, pp. 1094\u20131102 (2013)"},{"key":"9331_CR11","unstructured":"Busa-Fekete, R., H\u00fcllermeier, E., Sz\u00f6r\u00e9nyi, B.: Preference-based rank elicitation using statistical models: the case of mallows. In: Proceedings of The 31st International Conference on Machine Learning, vol.\u00a032 (2014)"},{"key":"9331_CR12","doi-asserted-by":"crossref","unstructured":"Cantador, I., Brusilovsky, P., Kuflik, T.: 2nd Workshop on information heterogeneity and fusion in recommender systems (hetrec 2011). In: Proceedings of the 5th ACM Conference on Recommender Systems, RecSys 2011. ACM, New York, NY, USA (2011)","DOI":"10.1145\/2043932.2044016"},{"issue":"3","key":"9331_CR13","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1137\/0502040","volume":"2","author":"BC Carlson","year":"1971","unstructured":"Carlson, B.C.: Appell functions and multiple averages. SIAM J. Math. Anal. 2(3), 420\u2013430 (1971). https:\/\/doi.org\/10.1137\/0502040","journal-title":"SIAM J. Math. Anal."},{"issue":"1","key":"9331_CR14","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1080\/10618600.2012.638220","volume":"21","author":"F Caron","year":"2012","unstructured":"Caron, F., Doucet, A.: Efficient Bayesian inference for generalized Bradley\u2013Terry models. J. Comput. Graph. Stat. 21(1), 174\u2013196 (2012)","journal-title":"J. Comput. Graph. Stat."},{"key":"9331_CR15","doi-asserted-by":"crossref","unstructured":"Carpenter, B., Gelman, A., Hoffman, M.D., Lee, D., Goodrich, B., Betancourt, M., Brubaker, M., Guo, J., Li, P., Riddell, A.: Stan: A probabilistic programming language. J. Stat. Softw. 76(1) (2017)","DOI":"10.18637\/jss.v076.i01"},{"key":"9331_CR16","unstructured":"\u00c7apan, G., Bozal, \u00d6., G\u00fcndo\u011fdu, \u0130., Cemgil, A.T.: Towards fair personalization by avoiding feedback loops. In: NeurIPS 2019 Workshop on Human-Centric Machine Learning (2019)"},{"key":"9331_CR17","unstructured":"Chakrabarti, D., Kumar, R., Radlinski, F., Upfal, E.: Mortal multi-armed bandits. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds) Advances in Neural Information Processing Systems, vol.\u00a021 (2009)"},{"key":"9331_CR18","doi-asserted-by":"publisher","unstructured":"Chaney, A.J.B., Stewart, B.M., Engelhardt, B.E.: How algorithmic confounding in recommendation systems increases homogeneity and decreases utility. In: Proceedings of the 12th ACM Conference on Recommender Systems, pp. 224\u2013232 (2018). https:\/\/doi.org\/10.1145\/3240323.3240370","DOI":"10.1145\/3240323.3240370"},{"key":"9331_CR19","unstructured":"Chen, J., Dong, H., Wang, X., Feng, F., Wang, M., He, X.: Bias and debias in recommender system: a survey and future directions. arXiv:2010.03240 (2020)"},{"issue":"3","key":"9331_CR20","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1093\/biomet\/89.3.539","volume":"89","author":"N Chopin","year":"2002","unstructured":"Chopin, N.: A sequential particle filter method for static models. Biometrika 89(3), 539\u2013552 (2002)","journal-title":"Biometrika"},{"issue":"3","key":"9331_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00654ED1V01Y201507ICR043","volume":"7","author":"A Chuklin","year":"2015","unstructured":"Chuklin, A., Markov, I., de Rijke, M.: Click models for web search. Synth. Lect. Inf. Concepts Retr. Serv. 7(3), 1\u2013115 (2015). https:\/\/doi.org\/10.2200\/S00654ED1V01Y201507ICR043","journal-title":"Synth. Lect. Inf. Concepts Retr. Serv."},{"key":"9331_CR22","doi-asserted-by":"publisher","unstructured":"Covington, P., Adams, J., Sargin, E.: Deep neural networks for YouTube recommendations. In: Proceedings of the 10th ACM Conference on Recommender Systems, New York, NY, USA (2016). https:\/\/doi.org\/10.1145\/2959100.2959190","DOI":"10.1145\/2959100.2959190"},{"key":"9331_CR23","doi-asserted-by":"crossref","unstructured":"Craswell, N., Zoeter, O., Taylor, M., Ramsey, B.: An experimental comparison of click position-bias models. In: Proceedings of the 2008 International Conference on Web Search and Data Mining, pp. 87\u201394. ACM (2008)","DOI":"10.1145\/1341531.1341545"},{"issue":"3","key":"9331_CR24","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1093\/biomet\/60.3.477","volume":"60","author":"RR Davidson","year":"1973","unstructured":"Davidson, R.R., Solomon, D.L.: A Bayesian approach to paired comparison experimentation. Biometrika 60(3), 477\u2013487 (1973)","journal-title":"Biometrika"},{"issue":"383","key":"9331_CR25","doi-asserted-by":"publisher","first-page":"628","DOI":"10.2307\/2288131","volume":"78","author":"JM Dickey","year":"1983","unstructured":"Dickey, J.M.: Multiple hypergeometric functions: probabilistic interpretations and statistical uses. J. Am. Stat. Assoc. 78(383), 628\u2013637 (1983). https:\/\/doi.org\/10.2307\/2288131","journal-title":"J. Am. Stat. Assoc."},{"issue":"399","key":"9331_CR26","doi-asserted-by":"publisher","first-page":"773","DOI":"10.2307\/2288786","volume":"82","author":"JM Dickey","year":"1987","unstructured":"Dickey, J.M., Jiang, J., Kadane, J.B.: Bayesian methods for censored categorical data. J. Am. Stat. Assoc. 82(399), 773\u2013781 (1987). https:\/\/doi.org\/10.2307\/2288786","journal-title":"J. Am. Stat. Assoc."},{"key":"9331_CR27","unstructured":"Doucet, A., Johansen, A.: A tutorial on particle filtering and smoothing: Fifteen years later (01, 2008)"},{"issue":"2","key":"9331_CR28","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/0370-2693(87)91197-X","volume":"195","author":"S Duane","year":"1987","unstructured":"Duane, S., Kennedy, A.D., Pendleton, B.J., Duncan, R.: Hybrid Monte Carlo. Phys. Lett. B 195(2), 216\u2013222 (1987). https:\/\/doi.org\/10.1016\/0370-2693(87)91197-X","journal-title":"Phys. Lett. B"},{"key":"9331_CR29","doi-asserted-by":"crossref","unstructured":"Ermis, B., Ernst, P., Stein, Y., Zappella, G.: Learning to rank in the position based model with bandit feedback. In: Proceedings of the 29th ACM International Conference on Information and Knowledge Management, pp. 2405\u20132412 (2020)","DOI":"10.1145\/3340531.3412723"},{"key":"9331_CR30","unstructured":"Falahatgar, M., Orlitsky, A., Pichapati, V., Suresh, A.T.: Maximum selection and ranking under noisy comparisons. In: International Conference on Machine Learning, pp. 1088\u20131096 (2017)"},{"key":"9331_CR31","unstructured":"Gentile, C., Li, S., Zappella, G.: Online clustering of bandits. In: Proceedings of the 31st International Conference on International Conference on Machine Learning, vol. 32, pp. II\u2013757 (2014)"},{"issue":"4","key":"9331_CR32","first-page":"455","volume":"44","author":"WR Gilks","year":"1995","unstructured":"Gilks, W.R., Best, N.G., Tan, K.K.C.: Adaptive rejection Metropolis sampling within Gibbs sampling. J. R. Stat. Soc. Ser. C Appl. Stat. 44(4), 455\u2013472 (1995)","journal-title":"J. R. Stat. Soc. Ser. C Appl. Stat."},{"key":"9331_CR33","unstructured":"Gopalan, A., Mannor, S., Mansour, Y.: Thompson sampling for complex online problems. In: Proceedings of the 31st International Conference on Machine Learning, pp. 100\u2013108 (2014)"},{"key":"9331_CR34","doi-asserted-by":"crossref","unstructured":"Guiver, J., Snelson, E.: Bayesian inference for Plackett\u2013Luce ranking models. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 377\u2013384. ACM (2009)","DOI":"10.1145\/1553374.1553423"},{"key":"9331_CR35","unstructured":"Gumbel, E.J.: Statistical theory of extreme values and some practical applications: a series of lectures. Technical Report (1954)"},{"key":"9331_CR36","unstructured":"G\u00fcndo\u011fdu, \u0130: Sequential Monte Carlo approach to inference in Bayesian choice models. Master\u2019s Thesis, Bogazici University, (2019). https:\/\/github.com\/ilkerg\/preference-sampler\/raw\/master\/thesis.pdf"},{"issue":"11","key":"9331_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i11","volume":"33","author":"RKS Hankin","year":"2010","unstructured":"Hankin, R.K.S.: A generalization of the Dirichlet distribution. J. Stat. Softw. 33(11), 1\u201318 (2010). https:\/\/doi.org\/10.18637\/jss.v033.i11","journal-title":"J. Stat. Softw."},{"issue":"1","key":"9331_CR38","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1145\/963770.963772","volume":"22","author":"JL Herlocker","year":"2004","unstructured":"Herlocker, J.L., Konstan, J.A., Terveen, L.G., Riedl, J.T.: Evaluating collaborative filtering recommender systems. ACM Trans. Inf. Syst. 22(1), 5\u201353 (2004). https:\/\/doi.org\/10.1145\/963770.963772","journal-title":"ACM Trans. Inf. Syst."},{"key":"9331_CR39","doi-asserted-by":"publisher","unstructured":"Hu, Y., Koren, Y., Volinsky, C.: Collaborative filtering for implicit feedback datasets. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 263\u2013272 (2008). https:\/\/doi.org\/10.1109\/ICDM.2008.22","DOI":"10.1109\/ICDM.2008.22"},{"issue":"1","key":"9331_CR40","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1214\/aos\/1079120141","volume":"32","author":"DR Hunter","year":"2004","unstructured":"Hunter, D.R.: MM Algorithms for generalized Bradley\u2013Terry models. Ann. Stat. 32(1), 384\u2013406 (2004). https:\/\/doi.org\/10.1214\/aos\/1079120141","journal-title":"Ann. Stat."},{"key":"9331_CR41","unstructured":"Jamieson, K.G., Nowak, R.: Active ranking using pairwise comparisons. In: Advances in Neural Information Processing Systems, pp. 2240\u20132248 (2011)"},{"key":"9331_CR42","doi-asserted-by":"publisher","unstructured":"Jiang, R., Chiappa, S., Lattimore, T., Agyorgy, A., Kohli, P.: Degenerate feedback loops in recommender systems. In: Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society (2019). https:\/\/doi.org\/10.1145\/3306618.3314288","DOI":"10.1145\/3306618.3314288"},{"issue":"3","key":"9331_CR43","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1080\/10618600.1992.10474583","volume":"1","author":"TJ Jiang","year":"1992","unstructured":"Jiang, T.J., Kadane, J.B., Dickey, J.M.: Computation of Carlson\u2019s multiple hypergeometric function R for Bayesian applications. J. Comput. Graph. Stat. 1(3), 231\u2013251 (1992). https:\/\/doi.org\/10.1080\/10618600.1992.10474583","journal-title":"J. Comput. Graph. Stat."},{"key":"9331_CR44","doi-asserted-by":"publisher","unstructured":"Joachims, T., Raimond, Y., Koch, O., Dimakopoulou, M., Vasile, F., Swaminathan, A.: Reveal 2020: Bandit and reinforcement learning from user interactions. In: Fourteenth ACM Conference on Recommender Systems, RecSys \u201920, pp. 628\u2013629 (2020). https:\/\/doi.org\/10.1145\/3383313.3411536","DOI":"10.1145\/3383313.3411536"},{"key":"9331_CR45","unstructured":"Kawale, J., Bui, H.H., Kveton, B., Tran-Thanh, L., Chawla, S.: Efficient Thompson sampling for online matrix-factorization recommendation. In: Advances in Neural Information Processing Systems, pp. 1297\u20131305 (2015)"},{"key":"9331_CR46","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1007\/978-3-319-13129-0_40","volume-title":"Web and Internet Economics","author":"J Komiyama","year":"2014","unstructured":"Komiyama, J., Qin, T.: Time-decaying bandits for non-stationary systems. In: Liu, T.-Y., Qi, Q., Ye, Y. (eds.) Web and Internet Economics, pp. 460\u2013466. Springer International Publishing, Cham (2014)"},{"key":"9331_CR47","unstructured":"Komiyama, J., Honda, J., Kashima, H., Nakagawa, H.: Regret lower bound and optimal algorithm in dueling bandit problem. In: Conference on Learning Theory, pp. 1141\u20131154 (2015)"},{"key":"9331_CR48","unstructured":"Komiyama, J., Honda, J., Nakagawa, H.: Copeland dueling bandit problem: regret lower bound, optimal algorithm, and computationally efficient algorithm. In: International Conference on Machine Learning, pp. 1235\u20131244 (2016)"},{"key":"9331_CR49","first-page":"4998","volume":"30","author":"J Komiyama","year":"2017","unstructured":"Komiyama, J., Honda, J., Takeda, A.: Position-based multiple-play bandit problem with unknown position bias. Adv. Neural Inf. Process. Syst. 30, 4998\u20135008 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"9331_CR50","unstructured":"Kveton, B., Szepesv\u00e1ri, C., Wen, Z., Ashkan, A.: Cascading bandits: learning to rank in the cascade model. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, vol. 37, pp. 767\u2013776 (2015a)"},{"key":"9331_CR51","unstructured":"Kveton, B., Wen, Z. , Ashkan, A., Szepesv\u00e1ri, C.: Combinatorial cascading bandits. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, vol. 1, pp. 1450\u20131458 (2015b)"},{"key":"9331_CR52","doi-asserted-by":"publisher","unstructured":"Lattimore, T., Szepesv\u00e1ri, C.: Bandit Algorithms. Cambridge University Press (2020). https:\/\/doi.org\/10.1017\/9781108571401","DOI":"10.1017\/9781108571401"},{"key":"9331_CR53","unstructured":"Lattimore, T., Kveton, B., Li, S., Szepesv\u00e1ri, C.: Toprank: A practical algorithm for online stochastic ranking. In: Advances in Neural Information Processing Systems, pp. 3949\u20133958 (2018)"},{"key":"9331_CR54","doi-asserted-by":"publisher","first-page":"121","DOI":"10.2307\/2529308","volume":"33","author":"T Leonard","year":"1977","unstructured":"Leonard, T.: An alternative Bayesian approach to the Bradley\u2013Terry model for paired comparisons. Biometrics 33, 121\u2013132 (1977). https:\/\/doi.org\/10.2307\/2529308","journal-title":"Biometrics"},{"key":"9331_CR55","unstructured":"Levine, N., Crammer, K., Mannor, S.: Rotting bandits. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 3077\u20133086 (2017)"},{"key":"9331_CR56","doi-asserted-by":"crossref","unstructured":"Li, S., Karatzoglou, A., Gentile, C.: Collaborative filtering bandits. In: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 539\u2013548 (2016)","DOI":"10.1145\/2911451.2911548"},{"key":"9331_CR57","unstructured":"Liang, D., Charlin, L., Blei, D.M.: Causal inference for recommendation. In: UAI Workshop on Causation: Foundation to Application (2016a)"},{"key":"9331_CR58","doi-asserted-by":"publisher","unstructured":"Liang, D., Charlin, L., McInerney, J., Blei, D.M.: Modeling user exposure in recommendation. In: Proceedings of the 25th International Conference on World Wide Web, WWW \u201916, pp. 951\u2013961 (2016b). https:\/\/doi.org\/10.1145\/2872427.2883090","DOI":"10.1145\/2872427.2883090"},{"key":"9331_CR59","doi-asserted-by":"publisher","unstructured":"Liang, D., Krishnan, R.G., Hoffman, M.D., Jebara, T.: Variational autoencoders for collaborative filtering. In: Proceedings of the 2018 World Wide Web Conference, WWW \u201918. International World Wide Web Conferences Steering Committee, pp. 689\u2013698 (2018). https:\/\/doi.org\/10.1145\/3178876.3186150","DOI":"10.1145\/3178876.3186150"},{"key":"9331_CR60","doi-asserted-by":"crossref","unstructured":"Liu, T.-Y.: Learning to rank for information retrieval. Found. Trends\u00ae Inf.Retri. 3(3), 225\u2013331 (2009)","DOI":"10.1561\/1500000016"},{"key":"9331_CR61","unstructured":"Liu, Y., Li, L.: A map of bandits for e-commerce. In: KDD 2021 Workshop on Multi-Armed Bandits and Reinforcement Learning: Advancing Decision Making in E-Commerce and Beyond (2021)"},{"key":"9331_CR62","volume-title":"Individual Choice Behavior","author":"R Ducan Luce","year":"1959","unstructured":"Ducan Luce, R.: Individual Choice Behavior. Wiley, Hoboken (1959)"},{"key":"9331_CR63","doi-asserted-by":"publisher","unstructured":"Mehrotra, R., McInerney, J., Bouchard, H., Lalmas, M., Diaz, F.: Towards a fair marketplace: counterfactual evaluation of the trade-off between relevance, fairness and satisfaction in recommendation systems. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 2243\u20132251. ACM (2018). https:\/\/doi.org\/10.1145\/3269206.3272027","DOI":"10.1145\/3269206.3272027"},{"key":"9331_CR64","unstructured":"Mohajer, S., Suh, C., Elmahdy, A.: Active learning for top-$$k$$ rank aggregation from noisy comparisons. In: International Conference on Machine Learning, pp. 2488\u20132497 (2017)"},{"issue":"3","key":"9331_CR65","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1214\/aos\/1056562461","volume":"31","author":"RM Neal","year":"2003","unstructured":"Neal, R.M.: Slice sampling. Ann. Stat. 31(3), 705\u2013767 (2003)","journal-title":"Ann. Stat."},{"key":"9331_CR66","unstructured":"Nie, X., Tian, X., Taylor, J., Zou, J.: Why adaptively collected data have negative bias and how to correct for it. In: International Conference on Artificial Intelligence and Statistics, pp. 1261\u20131269 (2018)"},{"key":"9331_CR67","doi-asserted-by":"crossref","unstructured":"Pariser, E.: The filter bubble: What the internet is hiding from you. Penguin, UK (2011)","DOI":"10.3139\/9783446431164"},{"key":"9331_CR68","doi-asserted-by":"crossref","unstructured":"Plackett, R.L.: The analysis of permutations. Appl. Stat. pp. 193\u2013202 (1975)","DOI":"10.2307\/2346567"},{"key":"9331_CR69","doi-asserted-by":"publisher","unstructured":"Pearl, P., Chen, L., Rong, H.: Evaluating recommender systems from the user\u2019s perspective: survey of the state of the art. User Model. User-Adapt. Interact. 22(4\u20135), 317\u2013355 (2012). https:\/\/doi.org\/10.1007\/s11257-011-9115-7","DOI":"10.1007\/s11257-011-9115-7"},{"issue":"1","key":"9331_CR70","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1037\/a0021150","volume":"118","author":"M Regenwetter","year":"2011","unstructured":"Regenwetter, M., Dana, J., Davis-Stober, C.P.: Transitivity of preferences. Psychol. Rev. 118(1), 42 (2011). https:\/\/doi.org\/10.1037\/a0021150","journal-title":"Psychol. Rev."},{"key":"9331_CR71","doi-asserted-by":"crossref","unstructured":"Russo, D.J., Van Roy, B., Kazerouni, A., Osband, I., Wen, Z.: A tutorial on Thompson sampling. Found. Trends\u00ae Mach. Learn. 11(1), 1\u201396 (2018)","DOI":"10.1561\/2200000070"},{"key":"9331_CR72","unstructured":"Saha, A., Gopalan, A.: Battle of bandits. In: Proceedings of the Thirty-Forth Conference on Uncertainty in Artificial Intelligence, UAI, pp. 06\u201310 (2018)"},{"key":"9331_CR73","unstructured":"Saha, A., Gopalan, A.: Combinatorial bandits with relative feedback. In: Advances in Neural Information Processing Systems, pp. 983\u2013993 (2019)"},{"key":"9331_CR74","unstructured":"Schmit, S., Riquelme, C.: Human interaction with recommendation systems. In: Proceedings of the 21th International Conference on Artificial Intelligence and Statistics (2018)"},{"key":"9331_CR75","unstructured":"Schnabel, T., Swaminathan, A., Singh, A., Chandak, N., Joachims, T.: Recommendations as treatments: debiasing learning and evaluation. In: International Conference on Machine Learning, pp. 1670\u20131679 (2016)"},{"key":"9331_CR76","unstructured":"Sinha, A., Gleich, D.F., Ramani, K.: Deconvolving feedback loops in recommender systems. In: Advances in Neural Information Processing Systems, pp. 3243\u20133251 (2016)"},{"issue":"3","key":"9331_CR77","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/BF01075203","volume":"35","author":"B Sopher","year":"1993","unstructured":"Sopher, B.: Intransitive cycles: rational choice or random error? An answer based on estimation of error rates with experimental data. Theor. Decis. 35(3), 311\u2013336 (1993). https:\/\/doi.org\/10.1007\/BF01075203","journal-title":"Theor. Decis."},{"key":"9331_CR78","unstructured":"Sui, Y., Zhuang, V., Burdick, J.W., Yue, Y.: Multi-dueling bandits with dependent arms. In: Proceedings of the Thirty-Forth Conference on Uncertainty in Artificial Intelligence, UAI (2017)"},{"key":"9331_CR79","doi-asserted-by":"publisher","unstructured":"Sui, Y., Zoghi, M., Hofmann, K., Yue, Y.: Advancements in dueling bandits. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pp. 5502\u20135510 (2018). https:\/\/doi.org\/10.24963\/ijcai.2018\/776","DOI":"10.24963\/ijcai.2018\/776"},{"key":"9331_CR80","doi-asserted-by":"publisher","unstructured":"Sun, W., Khenissi, S., Nasraoui, O., Shafto, P.: Debiasing the human-recommender system feedback loop in collaborative filtering. In: Companion Proceedings of the 2019 World Wide Web Conference, WWW \u201919, pp.645\u2013651. Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3308560.3317303","DOI":"10.1145\/3308560.3317303"},{"key":"9331_CR81","unstructured":"Sz\u00f6r\u00e9nyi, B., Busa-Fekete, R., Paul, A., H\u00fcllermeier, E.: Online Rank elicitation for Plackett-Luce: a dueling bandits approach. In: Advances in Neural Information Processing Systems, pp. 604\u2013612 (2015)"},{"issue":"3\/4","key":"9331_CR82","doi-asserted-by":"publisher","first-page":"285","DOI":"10.2307\/2332286","volume":"25","author":"WR Thompson","year":"1933","unstructured":"Thompson, W.R.: On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 25(3\/4), 285\u2013294 (1933)","journal-title":"Biometrika"},{"key":"9331_CR83","unstructured":"Urvoy, T., Clerot, F., F\u00e9raud, R., Naamane, S.: Generic exploration and k-armed voting bandits. In: International Conference on Machine Learning, pp. 91\u201399 (2013)"},{"key":"9331_CR84","doi-asserted-by":"publisher","unstructured":"Wang, Y., Liang, D., Charlin, L., Blei, D.M.: Causal inference for recommender systems. In: Fourteenth ACM Conference on Recommender Systems, RecSys \u201920, pp. 426\u2013431 (2020). https:\/\/doi.org\/10.1145\/3383313.3412225","DOI":"10.1145\/3383313.3412225"},{"key":"9331_CR85","unstructured":"Wu, H., Liu, X.: Double Thompson sampling for dueling bandits. In: Advances in Neural Information Processing Systems, pp. 649\u2013657 (2016)"},{"key":"9331_CR86","doi-asserted-by":"publisher","unstructured":"Yang, S.-H., Long, B., Smola, A.J., Zha, H., Zheng, Z.: Collaborative competitive filtering: learning recommender using context of user choice. In: Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 295\u2013304. ACM (2011). https:\/\/doi.org\/10.1145\/2009916.2009959","DOI":"10.1145\/2009916.2009959"},{"issue":"2","key":"9331_CR87","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/0022-2496(77)90026-8","volume":"15","author":"JI Yellott Jr","year":"1977","unstructured":"Yellott, J.I., Jr.: The relationship between Luce\u2019s choice axiom, Thurstone\u2019s theory of comparative judgment, and the double exponential distribution. J. Math. Psychol. 15(2), 109\u2013144 (1977)","journal-title":"J. Math. Psychol."},{"key":"9331_CR88","unstructured":"Yue, Y., Joachims, T.: Beat the mean bandit. In: International Conference on Machine Learning, pp. 241\u2013248 (2011)"},{"issue":"5","key":"9331_CR89","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1016\/j.jcss.2011.12.028","volume":"78","author":"Y Yue","year":"2012","unstructured":"Yue, Y., Broder, J., Kleinberg, R.: The k-armed dueling bandits problem. J. Comput. Syst. Sci. 78(5), 1538\u20131556 (2012). https:\/\/doi.org\/10.1016\/j.jcss.2011.12.028","journal-title":"J. Comput. Syst. Sci."},{"key":"9331_CR90","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, W., Wang, J.: Interactive collaborative filtering. In: Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, pp. 1411\u20131420 (2013)","DOI":"10.1145\/2505515.2505690"},{"key":"9331_CR91","volume-title":"Human Behavior and the Principle of Least Effort","author":"GK Zipf","year":"1949","unstructured":"Zipf, G.K.: Human Behavior and the Principle of Least Effort. Addison Wesley Press Inc, Pearson (1949)"},{"key":"9331_CR92","unstructured":"Zoghi, M., Whiteson, S., Munos, R., Rijke, M.: Relative upper confidence bound for the k-armed dueling bandit problem. In: International Conference on Machine Learning, pp. 10\u201318 (2014a)"},{"key":"9331_CR93","doi-asserted-by":"publisher","unstructured":"Zoghi, M., Whiteson, S.A., De\u00a0Rijke, M., Munos, R.: Relative confidence sampling for efficient on-line ranker evaluation. In: ACM International Conference on Web Search and Data Mining, pp. 73\u201382 (2014b). https:\/\/doi.org\/10.1145\/2556195.2556256","DOI":"10.1145\/2556195.2556256"},{"key":"9331_CR94","unstructured":"Zoghi, M., Karnin, Z.S., Whiteson, S., De\u00a0Rijke, M.: Copeland dueling bandits. In: Advances in Neural Information Processing Systems, pp. 307\u2013315 (2015)"},{"key":"9331_CR95","unstructured":"Zoghi, M., Tunys, T., Ghavamzadeh, M., Kveton, B., Szepesvari, C., Wen, Z.: Online learning to rank in stochastic click models. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 4199\u20134208 (2017)"},{"key":"9331_CR96","unstructured":"Zong, S., Ni, H., Sung, K., Ke, N.R., Wen, Z., Kveton, B.: UAI, Cascading bandits for large-scale recommendation problems (2016)"}],"container-title":["User Modeling and User-Adapted Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11257-022-09331-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11257-022-09331-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11257-022-09331-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T10:14:56Z","timestamp":1666001696000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11257-022-09331-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,4]]},"references-count":96,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["9331"],"URL":"https:\/\/doi.org\/10.1007\/s11257-022-09331-0","relation":{},"ISSN":["0924-1868","1573-1391"],"issn-type":[{"type":"print","value":"0924-1868"},{"type":"electronic","value":"1573-1391"}],"subject":[],"published":{"date-parts":[[2022,6,4]]},"assertion":[{"value":"12 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}