Trust Modeling in Recommendation

2021-12-09
Demirci, Mehmet Utku
Karagöz, Pınar
In social networks, trust is a fundamental notion aecting the na-ture and the strength of ties between individuals. It is also a pieceof useful auxiliary information for improving the performance ofrecommendation systems. The number of ratings given by a user isminimal compared to all items in popular, widely-used e-commercesites. Therefore, the user-item matrix that is used in collaborativeltering suers from data sparsity, resulting in poor recommenda-tion quality. Another issue is the cold start problem, which occursfor the inclusion of new users and new items to the system. Trustnotion is helpful for alleviating the eect of these problems byproviding additional relationships between the users and pointingout strong relationships. Information as to the trust between userscan be explicitly available. However, such information is not widelyavailable, and hence implicit trust models have been employed.This work analyzes two sub-problems under trust modeling forrecommendation: (1) What is the relationship between explicit andimplicit trust scores, are they replaceable? (2) Can we model ex-plicit trust in a trust network? For the rst problem, we present animplicit trust model and analyze the compatibility of implicit andexplicit trust scores. For the second problem, we model explicit trustmodeling as a link prediction problem and analyze the performanceof the prediction models we generate on a set of benchmark datasets
MEDES '21: Proceedings of the 13th International Conference on Management of Digital EcoSystem

Suggestions

Explicit and implicit trust modeling compatibility and explicit trust link prediction in trust-based recommendation systems
Demirci, Mehmet Utku; Karagöz, Pınar; Department of Computer Engineering (2022-1-31)
In social networks, trust is a fundamental notion affecting the nature and the strength of ties between individuals. It is also a piece of useful auxiliary information for improving the performance of recommendation systems. The number of ratings given by a user is minimal compared to all items in popular, widely-used e-commerce sites. Therefore, the user-item matrix that is used in collaborative filtering suffers from data sparsity, resulting in poor recommendation quality. Another issue is the cold start ...
Trust in principals
Zayim Kurtay, Merve (Oxford University Press, 2020-09-01)
Trust is generally considered as the basis of relationships between major school stakeholders and contributes not only to productive attitudes and behaviors but also to the accomplishment of collective goals. The principal is the key person in creating the atmosphere and the conditions conducive to trust in which trust-based relationships among school constituencies can flourish. Specifically, school culture characterized by collegiality, professionalism, and consideration generally leads to higher trust in...
The relationship between regulatory focus and trust: The roles of regulatory closure and propensity to trust
Emirza, Sevgi; Karagonlar, Gökhan (Orta Doğu Teknik Üniversitesi (Ankara, Turkey), 2020-6)
Drawing on regulatory focus theory and regulatory closure argument, this study argues that self-regulation mechanisms influence trust among people during anonymous interactions. Prevention focus is generally associated with risk aversion and quest for security and hence expected to induce less trust compared to promotion focus. We proposed and tested the hypothesis that the effect of regulatory focus on trust is moderated by regulatory closure (presence or absence of goal fulfillment). In support of th...
Trust-Driven Entrepreneurship for Community Well-Being of Refugees and Their Local Hosts
Baktir, Zeynep; Watson, Forrest (SAGE Publications, 2020-07-01)
This article explores community well-being (CWB) outcomes of institutional trust (and distrust) through entrepreneurship in the context of a refugee-hosting society in Turkey. Existing studies show the positive relationship between institutional trust and quality of life (QOL) as well as entrepreneurship and QOL in subsistence contexts. This research, however, explores the relationship between institutional (dis)trust and entrepreneurship on a path to CWB with a special emphasis on refugee and local interac...
Decision making under uncertainty: factors influencing mate selection in a dating application simulation
Semchenko, Ayten Yeşim; Çakır, Murat Perit; Temürcü, Ceyhan; Department of Cognitive Sciences (2017)
Human social intentions are heavily influenced by their perceptions of others. In this study, the effect of perceived attractiveness is of particular interest. The purpose of this study is to explore the effect of perceived attractiveness on the likelihood of wanting to have sex and the likelihood of using condom among dating application users. In real dating application environments, there would be many uncontrolled variables (e.g., age, not/having common friends etc.) related to the profiles that the part...
Citation Formats
M. U. Demirci and P. Karagöz, “Trust Modeling in Recommendation,” presented at the MEDES ’21: Proceedings of the 13th International Conference on Management of Digital EcoSystem, Tunus, 2021, Accessed: 00, 2022. [Online]. Available: http://dx.doi.org/10.1145/3444757.3485105.