‫ یک معیار شباهت نوین پالایش مشارکتی در سامانه‌های توصیه‌گر

یک معیار شباهت نوین پالایش مشارکتی در سامانه‌های توصیه‌گر

مجتبی کاظمی, ساسان حسینعلی زاده

چکیده

سامانه‌های توصیه‌گر به سه دسته پالایش جمعیت شناختی، پالایش مبتنی بر محتوا و پالایش مشارکتی تقسیم‌بندی می‌گردند. پالایش مشارکتی مبتنی بر همسایگان به‌عنوان یکی از مهم‌ترین کلاس‌های پالایش مشارکتی، کاربرد گسترده‌ای در حوزه تجاری را داراست. کلید این رویکرد در یافتن کاربران و یا کالا‌هایی مشابه براساس ماتریس امتیازات کاربر- کالا بوده تا بتواند توصیه‌های مناسبی برای کاربران فراهم نماید. در این مقاله به‌منظور محاسبه شباهت میان کاربران، معیار مشابهت جدیدی را براساس همسایگان کاربران ارائه داده‌ایم تا عملکرد توصیه‌ها را زمانی که تعداد امتیازات کمی در دسترس باشد، بهبود بخشد. از این‌رو از رویکرد احتمالاتی برای مدل‌سازی معیار مشابهت پیشنهادی میان دو کاربر پیشنهاد شده است. به‌منظور نشان دادن اثربخشی معیار، عملکرد معیارهای مشابهت سنتی و مدرن را با معیار مشابهت پیشنهادی مقایسه کرده‌ایم. نتایج توصیه‌های صورت گرفته براساس معیارهای ارزیابی مختلف نشان‌دهنده این است که معیار مشابهت پیشنهادی عملکرد بهتری نسبت به دیگر معیارهای مشابهت در داده‌های پراکنده داراست.

کلمات کلیدی

سامانه های توصیه گر, پالایش مشارکتی, پالایش مشارکتی مبتنی بر همسایگان, معیار مشابهت کاربران, داده های پراکنده

مراجع

  • [1] A. J. Slywotzky, "The Age of Choiceboard," HarvardBusiness Review, vol. 78, no. 1, pp. 40-41, 2000.
  • [2] L. Terveen, and W. Hill, "Beyond recommender systems:Helping people help each other," HCI in the NewMillennium, vol. 1, pp. 487-509, 2001.
  • [3] N. Landia, and S. Anand, "Personalised tagrecommendation," Recommender Systems & the SocialWeb, New York, NY, USA, pp. 83-86, 2009.
  • [4] N. K. Ranjbar, and S. H. Alizadeh, "A fuzzyrecommender system for forecasting customer segmentationby multi-variable fuzzy rule interpolation," in Proceedings ofthe Fuzzy Systems (IFSC), 2013 13th Iranian Conference on,2013, pp. 1-5.
  • [5] D. Park, H. Kim, I. Choi, and J. Kim, "A literature reviewand classification of recommender systems research," ExpertSystems with Applications, vol. 39, no. 11, pp. 10059-10072,2012.
  • [6] L. Candillier, F. Meyer, and M. Boullé, "Comparingstate-of-the-art collaborative filtering systems," Machinelearning and data mining in pattern recognition, pp. 548-562,2007.
  • [7] J. Schafer, D. Frankowski, and J. Herlocker, "Collaborative filtering recommender systems," The adaptiveweb, pp. 291-324, 2007.
  • [8] X. Sun, F. Kong, and S. Ye, "A comparison of severalalgorithms for collaborative filtering in startup stage," inNetworking, Sensing and Control, 2005. Proceedings of theIEEE, 2005, pp. 25-28.
  • [9] X. Su, and T. Khoshgoftaar, "A survey of collaborativefiltering techniques,"Advances in artificial intelligence,2009, p. 4.
  • [10] C. Desrosiers, and G. Karypis, "A comprehensivesurvey of neighborhood-based recommendation methods,"Recommender systems handbook, pp. 107-144, 2011.
  • [11] J. Bobadilla, A. Hernando, F. Ortega, and J. Bernal, "Aframework for collaborative filtering recommender systems,"Expert Systems with Applications, vol. 38, no. 12, pp.14609-14623, 2011.
  • [12] L. Sheugh, and S. H.Alizadeh, "Merging similarity andtrust based social networks to enhance the accuracy of trust-aware recommender systems," Journal of Computer &Robotics, vol. 8, no. 2, pp. 43-51, 2015.
  • [13] L. Sheugh, and S. H. Alizadeh, "Merging similarity andtrust based social networks to enhance the accuracy of trust-aware recommender systems," Journal of Computer &Robotics, vol. 8, no. 2, pp. 43-51, 2015.
  • [14] J. Wang, A. D. Vries, and M. Reinders, "Unifying user-based and item-based collaborative filtering approaches bysimilarity fusion," in Proceedings of the 29th annualinternational ACM SIGIR conference on Research anddevelopment in information retrieval, 2006, pp. 501-508.
  • [15] L. Sheugh, and S. H.Alizadeh, "A note on pearsoncorrelation coefficient as ametric of similarity inrecommender system," in Proceedings of the AI & Robotics (IRANOPEN), 2015, 2015, pp. 1-6.
  • [16] J. Bobadilla, F. Ortega,A. Hernando, and A. Gutiérrez, "Recommender systems survey," Knowledge-based systems,vol. 46, pp. 109-132, 2013.
  • [17] Y. Koren, "Factor inthe neighbors: Scalable andaccurate collaborative filtering," ACM Transactions onKnowledge Discovery from Data (TKDD), vol. 4, no. 1, p. 1,2010.
  • [18] Y. Koren, "Factor inthe neighbors: Scalable andaccurate collaborative filtering," ACM Transactions onKnowledge Discovery from Data (TKDD), vol. 4, no. 1, p. 1,2010.
  • [19] K. Ali, and W. Van Stam, "TiVo: making showrecommendations using a distributed collaborative filteringarchitecture," in Proceedings of the tenth ACM SIGKDDinternational conference on Knowledge discovery and datamining, 2004, pp. 394-401.
  • [20] M. Ekstrand, J. Riedl, and J. Konstan, "CollaborativeFiltering Recommender Systems," Foundations and Trendsin Human-Computer Interaction, vol. 4, no. 2, pp. 81-173,2011.
  • [21] G. Linden, B. Smith, and J. York, "Amazon. comrecommendations: Item-to-item collaborative filtering,"IEEE Internet computing, vol.7, no. 1, pp.76-80, 2003.
  • [22] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl, "Item-based collaborative filtering recommendation algorithms," inProceedings of the 10th international conference on WorldWide Web, 2001, pp. 285-295.
  • [23] G. G. CHOWDHURY, Introduction to moderninformation retrieval. London,England: Facet Publishing,2010.
  • [24] U. Shardanand, and P. Maes, "Social informationfiltering: algorithms for automating "word of mouth," inProceedings of the SIGCHI conference on Human factors incomputing systems, 1995, pp. 210-217.
  • [25] H. J. Ahn, "A new similarity measure for collaborativefiltering to alleviate the new user cold-starting problem,"Information Sciences, vol. 178, no. 1, pp. 37-51, 2008.
  • [26] A. El-Saddik, H. Kim, and G. Jo, "Collaborative error-reflected models for cold-start recommender systems,"Decision Support Systems, vol. 51, no. 3, pp. 519-531, 2011.
  • [27] J. Bobadilla, F. Ortega, and A. Hernando, "Acollaborative filtering similarity measure based onsingularities," Information Processing & Management, vol.48, no. 2, pp. 204-217, 2012.
  • [28] J. Bobadilla, F. Ortega, and A. Hernando, "Acollaborative filtering similarity measure based onsingularities," Information Processing & Management, vol.48, no. 2, pp. 204-217, 2012.
  • [29] J. Bobadilla, F. Ortega, A. Hernando, and J. Bernal, "Acollaborative filtering approach to mitigate the new user coldstart problem," Knowledge-Based Systems, vol. 26, pp.225-238, 2012.
  • [30] H. Liu, Z. Hu, A. Mian, H. Tian, and X. Zhu, "A newuser similarity model toimprove the accuracy ofcollaborative filtering," Knowledge-Based Systems, vol. 56,pp. 156-166, 2014.
  • [31] B. K. Patra, R. Launonen, V. Ollikainen, and S. Nandi, "Exploiting Bhattacharyya similarity measure to diminishuser cold-start problem in sparsedata," in Proceedings of theInternational Conference on Discovery Science, 2014,pp. 252-263.
  • [32] B. K. Patra, R. Launonen, V. Ollikainen, and S. Nandi, "A new similarity measure using Bhattacharyya coefficientfor collaborative filtering in sparse data," Knowledge-BasedSystems, vol. 82, 2015.
  • [33] L. Zhen, G. Q. Huang, and Z. Jiang, "Collaborativefiltering based on workflow space," Expert Systems withApplications, vol. 36, no. 4, pp. 7873-7881, 2009.
  • [34] L. Zhen, G. Q. Huang, and Z. Jiang, "Recommendersystem based on workflow," Decision Support Systems,vol. 48, no. 1, pp. 237-245, 2009.
  • [35] L. Zhen, Z. Jiang, and H. Song, "Distributedrecommender for peer-to-peer knowledge sharing,"Information Sciences, vol. 180, no. 18, pp. 3546-3561, 2010.
  • [36] J. L. Herlocker, J. A. Konstan, L. G. Terveen, and J. T.Riedl, "Evaluating collaborative filtering recommender systems," ACM Transactions on Information Systems (TOIS), vol. 22, no. 1, pp. 5-53, 2004