Kybernetika 60 no. 4, 446-474, 2024

A new uncertainty-aware similarity for user-based collaborative filtering

Khadidja Belmessous, Faouzi Sebbak, M'hamed Mataoui and Walid CherifiDOI: 10.14736/kyb-2024-4-0446

Abstract:

User-based Collaborative Filtering (UBCF) is a common approach in Recommender Systems (RS). Essentially, UBCF predicts unprovided entries for the target user by selecting similar neighbors. The effectiveness of UBCF greatly depends on the selected similarity measure and the subsequent choice of neighbors. This paper presents a new Uncertainty-Aware Similarity measure ``UASim" which enhances CF by accurately calculating how similar, dissimilar, and uncertain users' preferences are. Uncertainty is a key factor of ``UASim" that is managed in the neighborhood selection step of CF. Extensive experimental evaluation, conducted on Flixter, Movielens-100K, and Movielens-1M datasets, indicates that ``UASim" shows better performance compared to many representative predefined similarity measures. The proposed measure demonstrates enhancements across various performance indicators, namely: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), coverage, and the F-score.

Keywords:

uncertainty, similarity, collaborative filtering, subjective logic

Classification:

68P10, 68P20, 68T37

References:

  1. Ch. C. Aggarwal et al.: Recommender systems, volume 1. 2016.   CrossRef
  2. F. J. Aherne, N. A. Thacker and P. I. Rockett: The bhattacharyya metric as an absolute similarity measure for frequency coded data. Kybernetika 34 (1998), 4, 363-368.   DOI:10.1016/S0932-4739(98)80004-7
  3. H. J. Ahn: A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem. Inform. Sci. 178 (2008), 1, 37-51.   DOI:10.1016/j.ins.2007.07.024
  4. H. Al-Bashiri, M. A. Abdulgabber, A. Romli and H. Kahtan: An improved memory-based collaborative filtering method based on the topsis technique. PloS one 13 (2018), 10. e0204434.   DOI:10.1371/journal.pone.0204434
  5. A. A Amer, H. I. Abdalla and L. Nguyen: Enhancing recommendation systems performance using highly-effective similarity measures. Knowledge-Based Systems 217 (2021), 106842.   DOI:10.1016/j.knosys.2021.106842
  6. P. B. Anand and R. Nath: Content-based recommender systems. In: Recommender System with Machine Learning and Artificial Intelligence: Practical Tools and Applications in Medical, Agricultural and Other Industries. 2020, pp. 165-195.   CrossRef
  7. Y. Ar, Ş. E. Amrahov, N. A. Gasilov and S. Y.-Sert: A new curve fitting based rating prediction algorithm for recommender systems. Kybernetika 58 (2022), 3, 440-455.   DOI:10.14736/kyb-2022-3-0440
  8. K. Belmessous, F. Sebbak, A. Batouche and et al.: Co-rating aware evidential user-based collaborative filtering recommender system. In: International Conference on Computing Systems and Applications, Springer 2022, 51-60.   DOI:10.1007/978-3-031-12097-8\_5
  9. M. Chen and P. Liu: Performance evaluation of recommender systems. Int. J. Performability Engrg. 13 (2017), 8, 1246.   DOI:10.1055/s-0036-1591686
  10. R. K. Dewi, A. W. Widodo, Y. A. Sari and N. I. M. Aziz: Rank consistency of topsis in mobile based recommendation system. In: Proc. 5th International Conference on Sustainable Information Engineering and Technology, ACM Digital Library 2020, pp. 107-112.   CrossRef
  11. J. Feng, X. Fengs, N. Zhang and J. Peng: An improved collaborative filtering method based on similarity. PLoS One 13 (2018), 9, e0204003.   DOI:10.1371/journal.pone.0204003
  12. Fethi Fkih: Similarity measures for collaborative filtering-based recommender systems: Review and experimental comparison. Journal of King Saud University-Computer and Information Sciences, 2021.   CrossRef
  13. S. Forouzandeh, M. Rostami and K. Berahmand: A hybrid method for recommendation systems based on tourism with an evolutionary algorithm and topsis model. Fuzzy Inform. Engrg. 14 (2022), 1, 26-50.   DOI:10.1080/16168658.2021.2019430
  14. D. Gavalas, Ch. Konstantopoulos, K. Mastakas and G. Pantziou: Mobile recommender systems in tourism. J. Network Computer Appl. 39 (2014), 319-333.   DOI:10.1016/j.jnca.2013.04.006
  15. A. Gazdar and L. Hidri: A new similarity measure for collaborative filtering based recommender systems. Knowledge-Based Syst. 188 (2020), 105058.   DOI:10.1016/j.knosys.2019.105058
  16. G. Guo, J. Zhang and N. Yorke-Smith: A novel bayesian similarity measure for recommender systems. In ACM, editor, {\em Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI)}, pages 2619-2625, 2013.   CrossRef
  17. F. M. Harper and J. A. Konstan: The movielens datasets: History and context. ACM Trans. Int. Intell. Systems (TIIS) 5 (2015), 4, 1-19.   CrossRef
  18. Ch. L. Hwang and K. Yoon: Multiple Attribute Decision Making: Methods and Applications A State-Of-The-Art Survey, volume 186. Springer Science Business Media, 2012.   CrossRef
  19. N. Idrissi and A. Zellou: A systematic literature review of sparsity issues in recommender systems. Social Network Anal. Mining 10 (2020), 1, 1-23.   CrossRef
  20. A. Jøsang: A logic for uncertain probabilities. Int. J. Uncertainty, Fuzziness Knowledge-Based Syst. 9 (2001), 3, 279-311.   DOI:10.1016/S0218-4885(01)00083-1
  21. A. Jøsang: Subjective Logic, volume 4. 2016.   CrossRef
  22. M. Karimi, D. Jannach and M. Jugovac: News recommender systems-survey and roads ahead. Inform. Process. Management 54 (2018), 6, 1203-1227.   DOI:10.1016/j.ipm.2018.04.008
  23. H. Khojamli and J. Razmara: Survey of similarity functions on neighborhood-based collaborative filtering. Expert Syst. Appl. 185 (2021), 115482.   DOI:10.1016/j.eswa.2021.115482
  24. K. Kim: A new similarity measure to increase coverage of rating predictions for collaborative filtering. Appl. Intell. 53 (2023), 23, 28804-28818.   DOI:10.1007/s10489-023-05041-1
  25. V. L. Chetana and H. Seetha: Handling massive sparse data in recommendation systems. J. Inform. Knowledge Management (2024), 2450021.   DOI:10.1142/s0219649224500217
  26. H. Liu, Z. Hu, A. Mian, H. Tian and X. Zhu: A new user similarity model to improve the accuracy of collaborative filtering. Knowledge-Based Syst. 56 (2014), 156-166.   DOI:10.1016/j.knosys.2013.11.006
  27. S. Manochandar and M. Punniyamoorthy: A new user similarity measure in a new prediction model for collaborative filtering. Appl. Intell. 51 (2021), 1, 586-615.   DOI:10.1007/s10489-020-01811-3
  28. M. Mataoui, F. Sebbak, A. H. Sidhoum, T. E. Harbi, M. R. Senouci and K. Belmessous: A hybrid recommendation system for researchgate academic social network. Social Network Anal. Mining 13 (2023), 1. 53.   DOI:10.1007/s13278-023-01056-1
  29. D. L. Olson: Comparison of weights in topsis models. Math. Comput. Modell. 40 (2004), 7-8, 721-727.   DOI:10.1016/j.mcm.2004.10.003
  30. H. Papadakis, An. Papagrigoriou, C. Panagiotakis, E. Kosmas and P. Fragopoulou: Collaborative filtering recommender systems taxonomy. Knowledge Inform. Syst. 64 (2022), 1, 35-74.   DOI:10.1007/s10115-021-01628-7
  31. B. K. Patra, R. Launonen, V. Ollikainen and S. Nandi: A new similarity measure using bhattacharyya coefficient for collaborative filtering in sparse data. Knowledge-Based Syst. 82 (2015), 163-177.   DOI:10.1016/j.knosys.2015.03.001
  32. F. Ricci, L. Rokach and B. Shapira: Context-aware recommender systems: recommender systems handbook. In: Recommender Systems Handbook, Springer, 2011, pp. 217-253.   CrossRef
  33. D. Roy and M. Dutta: A systematic review and research perspective on recommender systems. J. Big Data 9 (2022), 1, 59.   DOI:10.1186/s40537-022-00592-5
  34. P. Sánchez and A. Bellogín: Building user profiles based on sequences for content and collaborative filtering. Inform. Process. Management 56 (2019), 1, 192-211.   DOI:10.1016/j.ipm.2018.10.003
  35. R. Seth and A. Sharaff: A comparative overview of hybrid recommender systems: Review, challenges, and prospects. Data Mining Machine Learning Appl. (2022), 57-98.   DOI:10.1002/9781119792529.ch3
  36. M. Shojaei and H. Saneifar: MFSR: A novel multi-level fuzzy similarity measure for recommender systems. Expert Systems Appl. 177 (2021), 114969.   DOI:10.1016/j.eswa.2021.114969
  37. D. Valcarce, J. Parapar and Á. Barreiro: Finding and analysing good neighbourhoods to improve collaborative filtering. Knowledge-Based Syst. 159 (2018), 193-202.   DOI:10.1016/j.knosys.2018.06.030
  38. D. Wang, Y. Yih and M. Ventresca: Improving neighbor-based collaborative filtering by using a hybrid similarity measurement. Expert Syst. Appl. 160 (2020), 113651.   DOI:10.1016/j.eswa.2020.113651
  39. Y. Wang, J. Deng, J. Gao and P. Zhang: A hybrid user similarity model for collaborative filtering. Inform. Sci. 418 (2017), 102-118.   DOI:10.1016/j.ins.2017.08.008
  40. Y. Wang, P. Wang, Z. Liu and L. Y. Zhang: A new item similarity based on $\alpha$-divergence for collaborative filtering in sparse data. Expert Syst. Appl. 166 (2021), 114074.   DOI:10.1016/j.eswa.2020.114074
  41. X. Wu, B. Cheng and J. Chen: Collaborative filtering service recommendation based on a novel similarity computation method. IEEE Trans. Services Comput. 10 (2015), 3, 352-365.   DOI:10.1109/tsc.2015.2479228
  42. X. Wu, Y. Huang and S. Wang: A new similarity computation method in collaborative filtering-based recommendation system. In: 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall), IEEE, 2017, pp. 1-5.   DOI:10.1109/vtcfall.2017.8288359