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

StatusVoR
Simple item page
cris.lastimport.scopus2025-04-17T03:12:29Z
dc.abstract.enRecommendation 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.
dc.affiliationWydział Projektowania w Warszawie
dc.affiliationInstytut Psychologii
dc.contributor.authorPawłowska, Justyna
dc.contributor.authorRydzewska, Klara
dc.contributor.authorWierzbicki, Adam
dc.date.access2023-03-11
dc.date.accessioned2024-01-04T07:41:39Z
dc.date.available2024-01-04T07:41:39Z
dc.date.created2023-02-14
dc.date.issued2023-03-11
dc.description.abstract<jats:title>Abstract</jats:title> <jats:p>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.</jats:p>
dc.description.accesstimeat_publication
dc.description.grantnumber2018/29/B/HS6/02604
dc.description.granttitleWspieranie ludzi w starszym wieku w dokonywaniu bardziej optymalnych wyborów w złożonych zadaniach decyzyjnych dotyczących zakupów internetowych
dc.description.issue2
dc.description.physical73-94
dc.description.versionfinal_published
dc.description.volume13
dc.identifier.doi10.2478/jaiscr-2023-0008
dc.identifier.eissn2449-6499
dc.identifier.issn2083-2567
dc.identifier.urihttps://share.swps.edu.pl/handle/swps/288
dc.identifier.weblinkhttps://www.proquest.com/docview/2785483138?sourcetype=Scholarly%20Journals
dc.languageen
dc.pbn.affiliationpsychologia
dc.rightsCC-BY-NC-ND
dc.rights.questionYes_rights
dc.share.articleOPEN_JOURNAL
dc.subject.enrecommender systems
dc.subject.encognitive limitations
dc.subject.enaging
dc.subject.ene-commerce
dc.swps.sciencecloudnosend
dc.titleUsing cognitive models to understand and counteract the effect of self-induced bias on recommendation algorithms
dc.title.journalJournal of Artificial Intelligence and Soft Computing Research
dc.typeJournalArticle
dspace.entity.typeArticle