Andrea Lisi
Laura Ricci
ABSTRACT
Recommender Systems are very popular tools within the online community, suggesting to their users a big variety of items like products, videos, music and locations to visit. Moreover, users actively populate these systems sending and reading opinions under the form of reviews, and potentially obtaining a reward for their activities. However, such systems typically rely on a central authority that acts as a trusted party having total control over the system. Decentralized Recommender Systems have been proposed to solve such issue distributing the control and responsibility on the hands of their users, but leading to risks in case of disputes or misbehaviour. Based on a general architecture of a Decentralized Recommender System, in this paper we identify the potential unfair exchanges that may rise during the activity between two users, and we propose a solution based on the concept of atomic swaps inherited from the blockchain technology. Finally, we provide an attack model to show that the proposed solution creates fair processes.
- G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE transactions on knowledge and data engineering, 17(6):734–749, 2005.Google Scholar
Digital Library
- P. Avesani, P. Massa, and R. Tiella. Moleskiing: a trust-aware decentralized recommender system. In 1stWorkshop on Friend of a Friend, Social Networking and the Semantic Web, 2004.Google Scholar
- F. Hendrikx, K. Bubendorfer, and R. Chard. Reputation systems: A survey and taxonomy. Journal of Parallel and Distributed Computing, 75:184–197, 2015.Google ScholarDigital Library
- M. Herlihy. Atomic cross-chain swaps. In Proceedings of the 2018 ACM symposium on principles of distributed computing, pages 245–254, 2018.Google ScholarDigital Library
- N. Hu, I. Bose, N. S. Koh, and L. Liu. Manipulation of online reviews: An analysis of ratings, readability, and sentiments. Decision support systems, 52(3):674–684,2012.Google Scholar
- A. Lisi, A. De Salve, P. Mori, and L. Ricci. A smart contract based recommender system. In International Conference on the Economics of Grids, Clouds, Systems, and Services, pages 29–42. Springer, 2019.Google Scholar
- D. Mayzlin, Y. Dover, and J. Chevalier. Promotional reviews: An empirical investigation of online review manipulation. American Economic Review, 104(8):2421–55, 2014.Google ScholarCross Ref
- S. Nakamoto. Bitcoin: A peer-to-peer electronic cash system. Technical report, Manubot, 2019.Google Scholar
- T. G. Papaioannou, J.-E. Ranvier, A. Olteanu, and K. Aberer. A decentralized recommender system for effective web credibility assessment. In Proceedings of the 21st ACM international conference on In formation and knowledge management, pages 704–713, 2012.Google ScholarDigital Library
- P. Phillips, S. Barnes, K. Zigan, and R. Schegg. Understanding the impact of online reviews on hotel performance: an empirical analysis. Journal of Travel Research, 56(2):235–249, 2017.Google ScholarCross Ref
- F. Ricci, L. Rokach, and B. Shapira. Recommenders ystems: introduction and challenges. In Recommender systems handbook, pages 1–34. Springer, 2015.Google Scholar
- D. Rosaci and G. M. Sarn ́e. Efficient personalization of e-learning activities using a multi-device decentralized recommender system. Computational Intelligence,26(2):121–141, 2010.Google ScholarCross Ref
- G. Ruffo and R. Schifanella. A peer-to-peer recommender system based on spontaneous affinities. ACM Transactions on Internet Technology, 9(1):1–34, 2009.Google ScholarDigital Library
- K. Salah, A. Alfalasi, and M. Alfalasi. A blockchain-based system for online consumer reviews. In IEEE Conference on Computer Communications Workshops, pages 853–858. IEEE, 2019Google Scholar
- M. Schuckert, X. Liu, and R. Law. Insights into suspicious online ratings: direct evidence from tripadvisor. Asia Pacific Journal of Tourism Research, 21(3):259–272, 2016.Google ScholarCross Ref
- S. Schulte, M. Sigwart, P. Frauenthaler, and M. Borkowski. Towards blockchain interoperability. In International Conference on Business Process Management, pages 3–10. Springer, 2019.Google Scholar
- Z. Wang, X. Liu, S. Chang, J. Zhou, G.-J. Qi, and T. S. Huang. Decentralized recommender systems. arXiv preprint arXiv:1503.01647, 2015.Google Scholar
- B. Wiki. Hashed time-lock contracts, 2018.Google Scholar
- W. Woerndl, M. Brocco, and R. Eigner. Context-aware recommender systems in mobile scenarios. International Journal of Information Technology and Web Engineering, 4(1):67–85, 2009.Google ScholarCross Ref
- G. Wood Ethereum: A secure decentralised generalised transaction ledger. Ethereum project yellow paper, 151(2014):1–32, 2014.Google Scholar
- Y. Xiao, N. Zhang, W. Lou, and Y. T. Hou. A survey of distributed consensus protocols for blockchain networks. IEEE Communications Surveys & Tutorials, 22(2):1432–1465, 2020.Google ScholarCross Ref
- Y. Zhang, R. Deng, X. Liu, and D. Zheng. Outsourcing service fair payment based on blockchain and its applications in cloud computing. IEEE Transactions on Services Computing, 2018.Google ScholarCross Ref
- J.-Y. Zi ́e, J.-C. Deneuville, J. Briffaut, and B. Nguyen. Extending atomic chain swaps. In ESORICS 2019, Data Privacy Management, Cryptocurrencies and Blockchain Technology, volume 11737, pages 219–229, 2019.Google Scholar
Recommendations
Investigating serendipity in recommender systems based on real user feedback
SAC '18: Proceedings of the 33rd Annual ACM Symposium on Applied ComputingOver the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-...
Acquiring User Information Needs for Recommender Systems
WI-IAT '13: Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 03Most recommender systems attempt to use collaborative filtering, content-based filtering or hybrid approach to recommend items to new users. Collaborative filtering recommends items to new users based on their similar neighbours, and content-based ...
A Scalable, Accurate Hybrid Recommender System
WKDD '10: Proceedings of the 2010 Third International Conference on Knowledge Discovery and Data MiningRecommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given resource. There are three main types of recommender systems: collaborative filtering, content-based filtering, and ...
Comments