Using cognitive models to understand and counteract the effect of self-induced bias on recommendation algorithms

• Autorzy: Pawłowska Justyna , Rydzewska Klara , Wierzbicki Adam

Identyfikatory

DOI

10.2478/jaiscr-2023-0008

• Języki publikacji: EN

Abstrakty

EN

Recommendation algorithms trained on a training set containing sub-optimal decisions may increase the likelihood of making more bad decisions in the future. We call this harmful effect self-induced bias, to emphasize that the bias is driven directly by the user’s past choices. In order to better understand the nature of self-induced bias of recommendation algorithms that are used by older adults with cognitive limitations, we have used agent-based simulation. Based on state-of-the-art results in psychology of aging and cognitive science, as well as our own empirical results, we have developed a cognitive model of an e-commerce client that incorporates cognitive decision-making abilities. We have evaluated the magnitude of self-induced bias by comparing results achieved by simulated agents with and without cognitive limitations due to age. We have also proposed new recommendation algorithms designed to counteract self-induced bias. The algorithms take into account user preferences and cognitive abilities relevant to decision making. To evaluate the algorithms, we have introduced 3 benchmarks: a simple product filtering method and two types of widely used recommendation algorithms: Content-Based and Collaborative filtering. Results indicate that the new algorithms outperform benchmarks both in terms of increasing the utility of simulated agents (both old and young), and in reducing self-induced bias.

Słowa kluczowe

EN

recommender system; cognitive limitations; aging; e-commerce

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2023
• Tom: Vol. 13, No. 2
• Strony: 73--94
• Opis fizyczny: Bibliogr. 65 poz., rys.

Twórcy

autor

Pawłowska Justyna

• Polish-Japanese Academy of Information Technology, Koszykowa 86, 02-008 Warsaw, Poland

• https://orcid.org/0000-0002-2070-6268

autor

Rydzewska Klara

• SWPS University of Social Sciences and Humanities, Chodakowska 19/31, 03-815 Warsaw, Poland

• https://orcid.org/0000-0002-5683-6320

autor

Wierzbicki Adam

• Polish-Japanese Academy of Information Technology, Koszykowa 86, 02-008 Warsaw, Poland

• https://orcid.org/0000-0003-0075-7030

Bibliografia

• [1] A. Kovalenko, Older adults shopping online: A fad or a trend?, In: The Impact of Covid-19 on E-Commerce. Proud Pen, 2020.
• [2] Q. Ma, A. H. Chan, and P.-L. Teh, Bridging the digital divide for older adults via observational training: Effects of model identity from a generational perspective, Sustainability, vol. 12, 2020, p. 4555.
• [3] Pew-Research, Internet/Broadband Fact Sheet, Pew Research Center, 2021.
• [4] Nielsen-Norman, UX Design for Seniors (Ages 65 and older), Nielsen Norman Group, 2020.
• [5] G. Sedek, P. Verhaeghen, and M. Martin, Social and motivational compensatory mechanisms for age-related cognitive decline, Psychology Press,2012.
• [6] T. M. Hess, Selective engagement of cognitive resources: Motivational influences on older adults’ cognitive functioning, Persp. Psychol. Science, vol. 9, 2014, pp. 388–407.
• [7] G. Sedek, T. Hess, and D. Touron, Multiple Pathways of Cognitive Aging: Motivational and Contextual Influences, Oxford University Press, 2021.
• [8] B. Knowles, V. Hanson, Y. Rogers, A. M. Piper, J. Waycott, N. Davies, A. Ambe, R. N. Brewer, D. Chattopadhyay, M. Deepak-Gopinath, et al.,The harm in conflating aging with accessibility, Comm. of the ACM, 2020.
• [9] R. Nielek, J. Pawlowska, K. Rydzewska, and A. Wierzbicki, Adapting algorithms on the web to deal with cognitive aging, Multiple Pathways of Cognitive Aging: Motivational and ContextualInfluences, 2021, p. 368.
• [10] R. Cabeza, Hemispheric asymmetry reduction in older adults: the harold model., Psychology and aging, vol. 17, 2002, p. 85.
• [11] D. Kahneman, Attention and effort, vol. 1063, Citeseer, 1973.
• [12] J. Cerella, Age-related decline in extrafoveal letter perception, Journal of Gerontology, vol. 40, 1985, pp. 727–736.
• [13] T. A. Salthouse and R. L. Babcock, Decomposing adult age differences in working memory., Developmental psychology, vol. 27, 1991, p. 763.
• [14] E. L. Glisky, Changes in cognitive function in human aging, Brain aging, 2007, pp. 3–20.
• [15] P. A. Reuter-Lorenz and C.-Y. C. Sylvester, The cognitive neuroscience of working memory and aging., 2005.
• [16] W. Bruine de Bruin, A. M. Parker, and B. Fischhoff, Decision-making competence: More than intelligence?, Curr. Directions in Psych. Science, vol. 29, 2020, pp. 186–192.
• [17] R. Mata, L. J. Schooler, and J. Rieskamp, The aging decision maker: cognitive aging and the adaptive selection of decision strategies., Psych. and aging, vol. 22, 2007, p. 796.
• [18] R. Mata, B. von Helversen, and J. Rieskamp, Learning to choose: Cognitive aging and strategy selection learning in decision making., Psych. and aging, vol. 25, 2010, p. 299.
• [19] G. Gigerenzer and D. G. Goldstein, Reasoning the fast and frugal way: models of bounded rationality., Psychological review, vol. 103, 1996, p. 650.
• [20] T. M. Hess, T. L. Queen, and T. R. Patterson, To deliberate or not to deliberate: Interactions between age, task characteristics, and cognitive activity on decision making, Journal of Behavioral Decision Making, vol. 25, 2012, pp. 29–40.
• [21] G. e. a. Chasseigne, Aging and probabilistic learning in single-and multiple-cue tasks, Experimental Aging Research, vol. 30, 2004, pp. 23–45.
• [22] G. R. Samanez-Larkin, S. E. Gibbs, K. Khanna, L. Nielsen, L. L. Carstensen, and B. Knutson, Anticipation of monetary gain but not loss in healthy older adults, Nature neuroscience, vol. 10, 2007, pp. 787–791.
• [23] E. Lex, D. Kowald, P. Seitlinger, T. N. T. Tran, A. Felfernig, M. Schedl, et al., Psychologyinformed recommender systems, Foundations and Trends⃝R in Information Retrieval, vol. 15, 2021, pp. 134–242.
• [24] E. Rich, User modeling via stereotypes, Cognitive science, vol. 3, 1979, pp. 329–354.
• [25] N. A. ALRossais and D. Kudenko, Evaluating stereotype and non-stereotype recommender systems., In: KaRS@ RecSys, 2018, pp. 23–28.
• [26] M. F. Rutledge-Taylor, A. Vellino, and R. L. West,A holographic associative memory recommender system, In: 2008 Third International Conference on Digital Information Management. IEEE, 2008, pp. 87–92.
• [27] D. Bollen, M. Graus, and M. C. Willemsen, Remembering the stars? effect of time on preference retrieval from memory, In: Proceedings of the sixth ACM conference on Recommender systems, 2012, pp. 217–220.
• [28] H. Ebbinghaus, Memory: A contribution to experimental psychology, Annals of neurosciences, vol. 20, 2013, p. 155.
• [29] H. Yu and Z. Li, A collaborative filtering method based on the forgetting curve, In: 2010 International conference on web information systems and mining, vol. 1. IEEE, 2010, pp. 183–187.
• [30] L. Ren, A time-enhanced collaborative filtering approach, In: 2015 4th International Conference on Next Generation Computer and Information Technology (NGCIT). IEEE, 2015, pp. 7–10.
• [31] A. Chmiel and E. Schubert, Using psychological principles of memory storage and preference to improve music recommendation systems, Leonardo Music Journal, vol. 28, 2018, pp. 77–81.
• [32] Z. Yang, J. He, and S. He, A collaborative filtering method based on forgetting theory and neural item embedding, In: 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). IEEE, 2019, pp. 1606–1610.
• [33] J. R. Anderson, M. Matessa, and C. Lebiere, Act-r: A theory of higher level cognition and its relations to visual attention, Human–Computer Interaction, vol. 12, 1997, pp. 439–462.
• [34] L. Van Maanen and J. N. Marewski, Recommender systems for literature selection: A competition between decision making and memory models, In: Proceedings of the 31st Annual Conference of the Cognitive Science Society. Austin, TX: Cognitive Science Society, 2009, pp. 2914–2919.
• [35] D. Kowald, P. Seitlinger, C. Trattner, and T. Ley,Long time no see: The probability of reusing tags as a function of frequency and recency, In: Proceedings of the 23rd International Conference on World Wide Web, 2014, pp. 463–468.
• [36] C. Trattner, D. Kowald, P. Seitlinger, S. Kopeinik, and T. Ley, Modeling activation processes in human memory to predict the reuse of tags, The Journal of Web Science, vol. 2, 2016.
• [37] D. Kowald, P. Seitlinger, S. Kopeinik, T. Ley, and C. Trattner, Forgetting the words but remembering the meaning: Modeling forgetting in a verbal and semantic tag recommender, In: Mining, Modeling, and Recommending’Things’ in Social Media, pp.75–95. Springer, 2013.
• [38] D. Kowald and E. Lex, The influence of frequency,recency and semantic context on the reuse of tags in social tagging systems, In: Proceedings of the 27th ACM Conference on Hypertext and Social Media, 2016, pp. 237–242.
• [39] C. Stanley and M. D. Byrne, Comparing vectorbased and bayesian memory models using largescale datasets: User-generated hashtag and tag prediction on twitter and stack overflow., Psychological Methods, vol. 21, 2016, p. 542.
• [40] M. C. Mozer and R. V. Lindsey, Predicting and improving memory retention: Psychological theory matters in the big data era, In: Big data in cognitive science, pp. 43–73. Psychology Press, 2016.
• [41] L. Li, W. Chu, J. Langford, and R. E. Schapire, A contextual-bandit approach to personalized newsarticle recommendation, In: Proceedings of the 19th international conference on World wide web, 2010, pp. 661–670.
• [42] J.-C. Shi, Y. Yu, Q. Da, S.-Y. Chen, and A.-X. Zeng, Virtual-taobao: Virtualizing real-world online retail environment for reinforcement learning, In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 2019, pp. 4902–4909.
• [43] D. Rohde, S. Bonner, T. Dunlop, F. Vasile, and A. Karatzoglou, Recogym: A reinforcement learning environment for the problem of product recommendation in online advertising, arXiv preprint arXiv:1808.00720, 2018.
• [44] E. Ie, C.-w. Hsu, M. Mladenov, V. Jain, S. Narvekar, J. Wang, R. Wu, and C. Boutilier, Recsim: A configurable simulation platform for recommender systems, arXiv preprint arXiv:1909.04847, 2019.
• [45] M. R. Santana, L. C. Melo, F. H. Camargo, B. Brandao, A. Soares, R. M. Oliveira, and S. Caetano, Mars-gym: A gym framework to model, train, and evaluate recommender systems for marketplaces, In: 2020 International Conference on Data Mining Workshops (ICDMW). IEEE, 2020, pp. 189–197.
• [46] B. Shi, M. G. Ozsoy, N. Hurley, B. Smyth, E. Z. Tragos, J. Geraci, and A. Lawlor, Pyrecgym: A reinforcement learning gym for recommender systems, In: Proceedings of the 13th ACM Conference on Recommender Systems, 2019, pp. 491–495.
• [47] L. Bernardi, S. Batra, and C. A. Bruscantini, Simulations in recommender systems: An industry perspective, arXiv preprint arXiv:2109.06723, 2021.
• [48] J. Huang, H. Oosterhuis, M. De Rijke, and H. Van Hoof, Keeping dataset biases out of the simulation: A debiased simulator for reinforcement learning based recommender systems, In: Fourteenth ACM conference on recommender systems, 2020, pp. 190–199.
• [49] J. Pawlowska, R. Nielek, and A. Wierzbicki, Lost in online stores? agent-based modeling of cognitive limitations of elderly online consumers, In: International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation. Springer, 2019, pp. 204–213.
• [50] J. Chen, H. Dong, X. Wang, F. Feng, M. Wang, and X. He, Bias and debias in recommender system: A survey and future directions, arXiv preprint arXiv:2010.03240, 2020.
• [51] A. Olteanu, C. Castillo, F. Diaz, and E. Kıcıman, Social data: Biases, methodological pitfalls, and ethical boundaries, Frontiers in Big Data, vol. 2, 2019, p. 13.
• [52] M. D. Ekstrand, M. Tian, I. M. Azpiazu, J. D. Ekstrand, O. Anuyah, D. McNeill, and M. S. Pera, All the cool kids, how do they fit in?: Popularity and demographic biases in recommender evaluation and effectiveness, In: Conference on fairness, accountability and transparency. PMLR, 2018, pp. 172–186.
• [53] M. J. Kusner, J. Loftus, C. Russell, and R. Silva, Counterfactual fairness, Advances in neural information processing systems, vol. 30, 2017.
• [54] C. Dimov, P. H. Khader, J. N. Marewski, and T. Pachur, How to model the neurocognitive dynamics of decision making: A methodological primer with act-r, Behavior research methods,; vol. 52, 2020, pp. 857–880.
• [55] K. Rydzewska, J. Pawłowska, R. Nielek, A. Wierzbicki, and G. Sedek, Cognitive limitations of older e-commerce customers in product comparison tasks, In: IFIP Conference on Human-Computer Interaction. Springer, 2021, pp. 646–656.
• [56] R. H. Logie and E. A. Maylor, An internet study of prospective memory across adulthood., Psychology and aging, vol. 24, 2009, p. 767.
• [57] B. Von Helversen, K. Abramczuk, W. Kopec, and R. Nielek, Influence of consumer reviews on online purchasing decisions in older and younger adults, Decision Support Systems, vol. 113, 2018, pp. 1–10.
• [58] R. Lambert-Pandraud, G. Laurent, and E. Lapersonne, Repeat purchasing of new automobiles by older consumers: empirical evidence and interpretations, Journal of Marketing, vol. 69, 2005, pp. 97–113.
• [59] J. R. Hauser, Consideration-set heuristics, Journal of Business Research, vol. 67, 2014, pp. 1688–1699.
• [60] J. R. Hauser, O. Toubia, T. Evgeniou, R. Befurt, and D. Dzyabura, Disjunctions of conjunctions, cognitive simplicity, and consideration sets, Journal of Marketing Research, vol. 47, 2010, pp. 485–496.
• [61] M. Ding, J. R. Hauser, S. Dong, D. Dzyabura, Z. Yang, S. Chenting, and S. P. Gaskin, Unstructured direct elicitation of decision rules, Journal of Marketing Research, vol. 48, 2011, pp. 116–127.
• [62] P. Lops, M. De Gemmis, and G. Semeraro, Content-based recommender systems: State of the art and trends, Recommender systems handbook, 2011, pp. 73–105.
• [63] C. Desrosiers and G. Karypis, A comprehensive survey of neighborhood-based recommendation methods, Recommender systems handbook, 2011, pp. 107–144.
• [64] L. Chen and P. Pu, Survey of preference elicitation methods, Technical report, 2004.
• [65] R. B. Nozari and H. Koohi, Novel implicit-trustnetwork-based recommendation methodology, Expert Systems with Applications, vol. 186, 2021, p. 115709.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).