Otokodlayıcılara dayalı hibrit çoklu-ölçütlü öneri algoritması

Öz

Çoklu-ölçütlü öneri sistemleri, aşırı bilgi sorunuyla başa çıkmak için birden fazla ölçütü dikkate alarak kişiselleştirilmiş öneriler üreterek etkili çözümler sunar. Çoklu-ölçütlü öneri sistemleri, geleneksel öneri sistemlerine göre kullanıcılarına daha doğru ve kişiselleştirilmiş öneriler sunsa da, artan kriter sayısı nedeniyle seyreklik bu tür sistemler için önemli bir sorun haline gelmektedir. Kullanıcılar arasında ortak puanlanan ögelerin olmamasndan dolayıı, komşuları bulmak ve doğru tahminler üretmek zorlaşmaktadır. Özellikle benzerlik-tabanlı çoklu-ölçütlü öneri yaklaşımları, seyreklik probleminden önemli ölçüde etkilenmektedir. Bu nedenle, bu çalışmada, bu sorunun olumsuz etkilerini en aza indirmek amacıyla, hem yorum hem de ölçüt derecelendirmelerinden otokodlayıcılar ile çıkarılan karmaşık, düşük boyutlu ve gizli özellikleri kullanan hibrit benzerlik-tabanlı çoklu-ölçütlü bir öneri algoritması önerilmiştir. Seyreklik yüzdesi %99,7235 olan gerçek bir veri seti üzerinde gerçekleştirilen deneysel sonuçlar, önerilen çalışmanın diğer komşuluk-tabanlı çok kriterli yaklaşımlara kıyasla daha doğru tahminler sağlayabildiğini göstermektedir.

Anahtar Kelimeler

• Çoklu-Ölçüt
• İşbirlikçi filtreleme
• Otokodlayıcılar
• Seyreklik
• Komşu seçimi

A hybrid multi-criteria recommendation algorithm based on autoencoders

Abstract

Multi-criteria recommender systems provide efficient solutions to deal with information overload problem by producing personalized recommendations considering multiple criteria. Even though multi-criteria recommender systems provide more accurate and personalized recommendations to their users compared with traditional recommender systems, sparsity becomes a major problem for such systems due to the increasing number of criteria. Due to the lack of co-rated items among users, finding out neighbors and producing accurate predictions become harder. Especially similarity-based multi-criteria recommendation approaches are significantly affected by the sparsity problem. Thus, aiming to minimize the negative impacts of that problem, a hybrid similarity-based multi-criteria recommendation method, that utilizes complex, low-dimensional and latent features obtained from both reviews and criteria ratings by autoencoders, is proposed in this work. The empirical results performed on a real data set with a sparsity percentage of 99.7235% show that the proposed work can provide more accurate predictions compared with other neighborhood-based multi-criteria approaches.

Keywords

• Multi-criteria
• Collaborative filtering
• Autoencoders
• Sparsity
• Neighbor selection

References

1. [1] Bulut H, Milli M. “New prediction methods for collaborative filtering”. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 22(2), 123-128, 2016.
2. [2] Adomavicius G, Kwon Y. “New recommendation techniques for multicriteria rating systems”. IEEE Intelligent Systems, 22(3), 48-55, 2007.
3. [3] Bilge A, Kaleli C. “A multi-criteria item-based collaborative filtering framework”. 11th International Joint Conference on Computer Science and Software Engineering, Chonburi, Thailand, 14-16 May 2014.
4. [4] Adomavicius G, Manouselis N, Kwon Y. Multi-Criteria Recommender Systems. Editors: Ricci F, Rokach L, Shapira B, Kantor PB. Recommender Systems Handbook, 769-803, Boston, MA, USA, Springer, 2011
5. [5] Altan G. “Breast cancer diagnosis using deep belief networks on ROI images”. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi 28(2), 286-291, 2021.
6. [6] Cevik F, Kilimci ZH. “The evaluation of Parkinson's disease with sentiment analysis using deep learning methods and word embedding models”. Pamukkale University Journal of Engineering Sciences 27(2), 151-161, 2021.
7. [7] Wang X, Kadıoğlu S. “Modeling uncertainty to improve personalized recommendations via bayesian deep learning”. International Journal of Data Science and Analytics, 16, 191-203, 2023.
8. [8] Du YP, Yao CQ, Huo SH, et al. “A new item-based deep network structure using a restricted boltzmann machine for collaborative filtering”. Frontiers of Information Technology & Electronic Engineering, 18(5), 658-666, 2017.

9. [9] Zhao Z, Yang Q, Lu H, Weninger T, Cai D, He X, Zhuang Y. “Social-aware movie recommendation via multimodal network learning”. IEEE Transactions on Multimedia, 20(2), 430-440, 2018.
10. [10] Chen X. “The application of neural network with convolution algorithm in western music recommendation practice”. Journal of Ambient Intelligence and Humanized Computing, 2020. https://doi.org/10.1007/s12652-020-01806-5.
11. [11] Batmaz Z, Kaleli C. “A new similarity-based multicriteria recommendation algorithm based on autoencoders”. Turkish Journal of Electrical Engineering & Computer Sciences, 30, 855-870, 2022.
12. [12] Kumar Bokde D. Girase S. Mukhopadhyay D. “An item-based collaborative filtering using dimensionality reduction techniques on mahout framework”. 4th Post Graduate Conference for Information Technology, Sangamner, Maharashtra, India, 24-25 March 2015.
13. [13] Nilashi M, Bin Ibrahim O, Ithnin N, et al. “A multi-criteria recommendation system using dimensionality reduction and neuro-fuzzy techniques”. Soft Computing, 19(11), 3173-320, 2015.
14. [14] Nilashi M, Esfahani MD, Roudbaraki MZ, et al. “A multi-criteria collaborative filtering recommender system using clustering and regression techniques”. Journal of Soft Computing and Decision Support Systems, 3(5), 24-30 2016.
15. [15] Shambour Q, Hourani M, Fraihat S. “An item-based multi-criteria collaborative filtering algorithm for personalized recommender systems”. International Journal of Advanced Computer Science and Applications, 7(8), 274-279, 2016.
16. [16] Kermany NR, Alizadeh SH. “A hybrid multi-criteria recommender system using ontology and neuro-fuzzy techniques”. Electronic Commerce Research and Applications, 21, 50-64, 2017.
17. [17] Fan J, Xu L. “A robust multi-criteria recommendation approach with preference-based similarity and support vector machine”. 10th International Symposium on Neural Networks, Dalian, China, 4-6 July 2013.
18. [18] Zhang K, Liu X, Wang W, Li J. “Multi-criteria recommender system based on social relationships and criteria preferences”. Expert Systems with Applications, 176, 114868-114882, 2021.
19. [19] Batmaz Z, Yurekli A, Bilge A, Kaleli C. “A review on deep learning for recommender systems: challenges and remedies”. Artificial Intelligence Review 52(1), 1-37, 2019.
20. [20] Gunawardana A, Meek C. “Tied boltzmann machines for cold start recommendations”. 2nd ACM Conference on Recommender Systems, Lausanne, Switzerland, 23-25 October 2008.
21. [21] Wang X, Wang Y. “Improving content-based and hybrid music recommendation using deep learning”. 22nd ACM International Conference on Multimedia, Orlando, Florida, USA, 3-7 November 2014.
22. [22] Zhang S, Yao L, Xu X. “Autosvd++ an efficient hybrid collaborative filtering model via contractive auto-encoders”. 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, Tokyo, Japan, 7-11 August 2017.
23. [23] Wei J, He J, Chen K, et al. “Collaborative filtering and deep learning based recommendation system for cold start items”. Expert Systems with Applications 69, 29-39, 2017.
24. [24] Lee J, Lee K, Park J, et al. “Deep content-user embedding model for music recommendation”. 2018. arXiv preprint arXiv:1807.06786.
25. [25] Seo S, Huang J, Yang H, et al. “Interpretable convolutional neural networks with dual local and global attention for review rating prediction”. 11th ACM Conference on Recommender Systems, Como, Italy, 27-31 August 2017.
26. [26] Paradarami TK, Bastian ND, Wightman JL. “A hybrid recommender system using artificial neural networks”. Expert Systems with Applications, 83, 300-313, 2017.
27. [27] Wang Z, Xia H, Chen S, et al. “Joint representation learning with ratings and reviews for recommendation”. Neurocomputing, 425, 181-190, 2021.
28. [28] Tallapally D, Sreepada RS, Patra BK, et al. “User preference learning in multi-criteria recommendations using stacked auto encoders”. 12th ACM Conference on Recommender Systems, Vancouver, BC, Canada, 2-7 October 2018.
29. [29] Batmaz Z, Kaleli C. “Ae-mccf: An autoencoder-based multi-criteria recommendation algorithm”. Arabian Journal for Science and Engineering, 44(11), 9235-9247, 2019.
30. [30] Nassar N, Jafar A, Rahhal Y. “A novel deep multi-criteria collaborative filtering model for recommendation system”. Knowledge-Based Systems, 187, 104811-104817 2020.
31. [31] Hasan, E., Ding, C., Cuzzocrea, “A. Multi-criteria rating and review based recommendation model”. 2022 IEEE International Conference on Big Data, Osaka, Japan, 17-20 December 2022.
32. [32] Wang, J. “Multi-criteria recommender system with hybrid deep tensor decomposition”. 4th International Conference on Data Storage and Data Engineering, Barcelona, Spain, 18-20 February 2021.
33. [33] Chen Z, Gai S, Wang D. “Deep tensor factorization for multi-criteria recommender systems”. 2019 IEEE International Conference on Big Data, Los Angeles, CA, USA, 9-12 December 2019.
34. [34] Goodfellow IJ, Bengio Y, Courville AC. Deep Learning. Adaptive Computation and Machine Learning, 1st ed. Massachusetts, USA, MIT Press, 2016.
35. [35] Uysal AK, Gunal S. “A novel probabilistic feature selection method for text classification”. Knowledge-Based Systems, 36, 226-235, 2012.
36. [36] Uysal AK, Gunal S. “The impact of preprocessing on text classification”. Information Processing & Management, 50(1), 104-112, 2014.
37. [37] Jannach D, Karakaya Z, Gedikli F. “Accuracy improvements for multi-criteria recommender systems”. 13th ACM Conference on Electronic Commerce, Valencia, Spain, 4-8 June 2012.
38. [38] Wang H, Lu Y, Zhai C. “Latent aspect rating analysis without aspect keyword supervision”. 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Diego, CA, USA, 21-24 August 2011.
39. [39] Ge M, Delgado-Battenfeld C, Jannach D. “Beyond accuracy: evaluating recommender systems by coverage and serendipity”. 2010 ACM Conference on Recommender Systems, Barcelona, Spain, 26-30 September 2010.