‫ تنوع‌بخشی شخصی‌سازی‌شده برای توصیه اقلام دنباله طولانی با استفاده از الگوریتم جستجوی ممنوعه چندهدفه

تنوع‌بخشی شخصی‌سازی‌شده برای توصیه اقلام دنباله طولانی با استفاده از الگوریتم جستجوی ممنوعه چندهدفه

الهه ملک‌زاده‌همدانی, مرجان کائدی

چکیده

در الگوریتم‌های توصیه‌ی رایج، تمرکز اصلی بر افزایش دقت توصیه‌ها است. این الگوریتم ها ممکن است قادر به یافتن تمامی اقلام مناسب برای توصیه به کاربران نباشند و تعداد زیادی از اقلام که توسط تعداد کمی از کاربران امتیازدهی شده‌اند، به ندرت در توصیه‌ها شرکت کنند. به این اقلام، اقلام دنباله طولانی گفته می‌شود. یکی از روش‌هایی که به مشارکت بیشتر اقلام دنباله طولانی کمک می‌کند توجه به ابعاد دیگری از سیستم توصیه‌گر مانند تنوع است. میزان گرایش کاربران به تنوع توصیه‌ها متفاوت است، بنابراین بهتر است تنوع‌بخشی متناسب با میزان تنوع‌گرایی کاربر انجام شود. در این پژوهش راه‌حلی مبتنی بر تنوع‌بخشی شخصی‌سازی‌شده برای مسئله عدم توصیه اقلام دنباله طولانی ارائه می شود. روش پیشنهادی یک روش بهینه‌سازی چندهدفه بر مبنای الگوریتم جستجوی ممنوعه است که در آن دو هدف برای توجه بیشتر به اقلام دنباله طولانی و یک هدف برای بهبود دقت لیست توصیه تعریف می‌شود. نتایج ارزیابی نشان می‌دهد که این روش در مقایسه با روش‌های قبلی کارایی بیشتری دارد و منجر به مشارکت بیشتر اقلام دنباله طولانی در توصیه ها می‌شود، ضمن اینکه دقت را در حد قابل قبولی حفظ می‌کند.

کلمات کلیدی

سیستم توصیه‌گر, تنوع، دنباله طولانی, بهینه‌سازی چندهدفه, جستجوی ممنوعه

مراجع

  • [1]G. Adomavicius and Y. Kwon, "Improving aggregate recommendation diversity using ranking-based techniques", IEEE Transactions on Knowledge and Data Engineering, vol. 24, no. 5, pp. 896-911, 2012.
  • [2] F. Ricci, L. Rokach, and B. Shapira, Introduction to Recommender Systems Handbook. Boston, MA, Springer US, 2011.
  • [3] K. Bradley and B. Smyth, Improving recommendation diversity, Proceedings of the Twelfth Irish Conference on Artificial Intelligence and Cognitive Science, pp. 85-94, Maynooth, Ireland, 2001.
  • [4] 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, vol. 17, no. 6, pp. 734-749, 2005.
  • [5] [W. Wu, L. Chen, and L. He, Using personality to adjust diversity in recommender systems, Proceedings of the 24th ACM Conference on Hypertext and Social Media, pp. 225-229, 2013.
  • [6] J. Borras, A. Moreno, and A. Valls, "Intelligent tourism recommender systems: A survey", Expert Systems with Applications, vol. 41, no. 16, pp. 7370-7389, 2014.
  • [7] D. Fleder and K. Hosanagar, "Blockbuster culture"s next rise or fall: The impact of recommender systems on sales diversity", Management science, vol. 55, no. 5, pp. 697-712, 2009.
  • [8] S. M. Mcnee, Meeting user information needs in recommender systems, Proquest, 2006.
  • [9] Y.-J. Park, "The adaptive clustering method for the long tail problem of recommender systems", IEEE Transactions on Knowledge and Data Engineering, vol. 25, no. 8, pp. 1904-1915, 2013.
  • [10] T. Di Noia, V. C. Ostuni, J. Rosati, P. Tomeo, and E. Di Sciascio, An analysis of users" propensity toward diversity in recommendations, Proceedings of the 8th ACM Conference on Recommender systems, pp. 285-288, 2014.
  • [11] C.-N. Ziegler, S. M. McNee, J. A. Konstan, and G. Lausen, Improving recommendation lists through topic diversification, Proceedings of the 14th international conference on World Wide Web, pp. 22-32, 2005.
  • [12] B. Smyth and P. McClave, Similarity vs. Diversity, Case-Based Reasoning Research and Development: 4th International Conference on Case-Based Reasoning, ICCBR 2001 Vancouver, pp. 347-361, Berlin, Heidelberg, 2001.
  • [13] N. Hurley and M. Zhang, "Novelty and diversity in top-n recommendation--analysis and evaluation", ACM Transactions on Internet Technology (TOIT), vol. 10, no. 4, p. 14, 2011.
  • [14] Y.-C. Ho, Y.-T. Chiang, and J. Y.-J. Hsu, Who likes it more?: mining worth-recommending items from long tails by modeling relative preference, Proceedings of the 7th ACM international conference on Web search and data mining, pp. 253-262, 2014.
  • [15] Y.-J. Park and A. Tuzhilin, The long tail of recommender systems and how to leverage it, Proceedings of the 2008 ACM conference on Recommender systems, pp. 11-18, 2008.
  • [16] G. Adomavicius and Y. Kwon, Overcoming accuracy-diversity tradeoff in recommender systems: a variance-based approach, Proceedings of the 18th workshop on information technology and systems (WITS’08), Paris, 2008.
  • [17] I. Avazpour, T. Pitakrat, L. Grunske, and J. Grundy, "Dimensions and metrics for evaluating recommendation systems," in Recommendation systems in software engineering, P. M. Robillard, W. Maalej, J. R. Walker, and T. Zimmermann, Eds. Berlin, Heidelberg: Springer, pp. 245-273, 2014.
  • [18] Ò. Celma, "The Long Tail in Recommender Systems," in Music Recommendation and Discovery: Springer, pp. 87-107, 2010.
  • [19] Y. Shi, X. Zhao, J. Wang, M. Larson, and A. Hanjalic, Adaptive diversification of recommendation results via latent factor portfolio, Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval, pp. 175-184, 2012.
  • [20] S. Vargas and P. Castells, Exploiting the diversity of user preferences for recommendation, Proceedings of the 10th Conference on Open Research Areas in Information Retrieval, pp. 129-136, 2013.
  • [21] L. Chen, W. Wu, and L. He, How personality influences users" needs for recommendation diversity?, CHI"13 Extended Abstracts on Human Factors in Computing Systems, pp. 829-834, 2013.
  • ی22و ا. ملک زاده همدانی و م. كائدي, توصیه اقلام دنباله طولانی با استفاده از تنوع‌بخشی شخصی‌سازی‌شده در سیستم‌های توصیه‌گر, بیست و دومین کنفرانس ملی سالانه انجمن کامپیوتر ایران, تهران, 1395.
  • [23] L. Chen, W. Wu, and L. He, "Personality and Recommendation Diversity," in Emotions and Personality in Personalized Services: Models, Evaluation and Applications, M. Tkalčič, B. De Carolis, M. de Gemmis, A. Odić, and A. Košir, Eds. Cham: Springer International Publishing, pp. 201-225, 2016.
  • [24] T. Di Noia, J. Rosati, P. Tomeo, and E. D. Sciascio, "Adaptive multi-attribute diversity for recommender systems", Information Sciences, vol. 382–383, pp. 234-253, 2017.
  • [25] B. Geng, L. Li, L. Jiao, M. Gong, Q. Cai, and Y. Wu, "NNIA-RS: A multi-objective optimization based recommender system", Physica A: Statistical Mechanics and its Applications, vol. 424, pp. 383-397, 2015.
  • [26] M. T. Ribeiro, A. Lacerda, A. Veloso, and N. Ziviani, Pareto-efficient hybridization for multi-objective recommender systems, Proceedings of the sixth ACM conference on Recommender systems, pp. 19-26, 2012.
  • [27] Y. Zuo, M. Gong, J. Zeng, L. Ma, and L. Jiao, "Personalized Recommendation Based on Evolutionary Multi-Objective Optimization", IEEE Computational Intelligence Magazine, vol. 10, no. 1, pp. 52-62, 2015.
  • [28] ی28د ا. ملک زاده همدانی و م. كائدي, "تنوع‌بخشی شخصی‌سازی‌شده در سیستم توصیه‌گر با استفاده از الگوریتم شبیه‌سازی تبرید دوهدفه", مجله علوم رايانشي, شماره 3, صص 67-82, 1395.
  • [29] K. Tso and L. Schmidt-Thieme, Attribute-aware collaborative filtering, Proceedings of the 29th Annual Conference of the Gesellschaft für Klassifikation e.V. University of Magdeburg, pp. 614-621, Berlin, Heidelberg, 2006.
  • [30] S. Wang, M. Gong, H. Li, and J. Yang, "Multi-objective optimization for long tail recommendation", Knowledge-Based Systems, vol. 104, pp. 145-155, July 2016.
  • [31] F. Glover, E. Taillard, and E. Taillard, "A user"s guide to tabu search", Annals of operations research, vol. 41, no. 1, pp. 1-28, 1993.
  • [32] I. H. Osman and N. Christofides, "Capacitated clustering problems by hybrid simulated annealing and tabu search", International Transactions in Operational Research, vol. 1, no. 3, pp. 317-336, 1994/07/01/ 1994.
  • [33] S. R. Thangiah, I. H. Osman, and T. Sun, "Hybrid genetic algorithm, simulated annealing and tabu search methods for vehicle routing problems with time windows", Computer Science Department, Slippery Rock University, Technical Report SRU CpSc-TR-94-27, vol. 69, 1994.
  • [34] Y. A. Katsigiannis, P. S. Georgilakis, and E. S. Karapidakis, "Hybrid Simulated Annealing–Tabu Search Method for Optimal Sizing of Autonomous Power Systems With Renewables", IEEE Transactions on Sustainable Energy, vol. 3, no. 3, pp. 330-338, 2012.
  • [35] K. Lenin, B. R. Reddy, and M. Suryakalavathi, "Hybrid Tabu search-simulated annealing method to solve optimal reactive power problem", International Journal of Electrical Power & Energy Systems, vol. 82, pp. 87-91, 2016.
  • [36] S. X. Zhao and C. Wang, "Research on Personalized Recommendation System Based on LBS", Research in Electronic Commerce Frontiers, vol. 2, pp. 1-5, 2014.
  • [37] P. Basile, A. Caputo, M. de Gemmis, P. Lops, and G. Semeraro, Modeling Short-Term Preferences in Time-Aware Recommender Systems, Proceedings of DeCAT - 1st Workshop on Deep Content Analytics Techniques for Personalized and Intelligent Services, co-located with UMAP 2015, Dublin, 2015.
  • [38] G. Adomavicius and Y. Kwon, Maximizing aggregate recommendation diversity: A graph-theoretic approach, Proceedings of the 1st International Workshop on Novelty and Diversity in Recommender Systems (DiveRS 2011), pp. 3-10, Chicago, 2011.
  • [39] S. Singh, S. Bag, and M. Jenamani, Relative similarity based approach for improving aggregate recommendation diversity, 2015 Annual IEEE India Conference (INDICON), pp. 1-6, 2015.
  • [40] .Movielens. Available: http://grouplens.org/datasets/movielens/, Mar. 2015
  • [41] Netflix Prize Dataset. Available: http://academictorrents.com/, May. 2015
  • [42] S. Vargas, Novelty and diversity enhancement and evaluation in Recommender Systems, Master"s Thesis, Autonomous University of Madrid, April 2012.
  • [43] L. Shi, Trading-off among accuracy, similarity, diversity, and long-tail: a graph-based recommendation approach, Proceedings of the 7th ACM conference on Recommender systems, pp. 57-64, 2013.