Journals / Journal of Advanced Research in Natural and Applied Sciences / 2019 / Cilt: 5 Sayı: 2

MovieANN: A Hybrid Approach to Movie Recommender Systems Using Multi Layer Artificial Neural Networks

MovieANN: Film Öneri Sistemlerine Çok Katmanlı Yapay Sinir Ağı Kullanarak Karma Bir Yaklaşım

Pages
214–232
Publication Date
2019-12-19
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The recommendation performance in terms of accuracy is 84.52%, 84.54% in terms of precision and 99.98% in terms of recall.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The amount of data in World Wide Web is growing exponentially.
📊
Key Findings & Data:The model is tested on a MoiveLens 1M dataset that consists of six thousand users, four thousand movies and one million ratings.
💡
Conclusion & Impact:The recommendation performance in terms of accuracy is 84.52%, 84.54% in terms of precision and 99.98% in terms of recall.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Öneri Sistemleri · İçerik Tabanlı Filtreleme · işbirlikçi Filtreleme

Abstract

The amount of data in World Wide Web is growing exponentially. Users are often lost in this vast ocean of data. In order to filter the valuable information from vast amount of data, recommendation systems are used. These systems are based on collaborative filtering, content based filtering and hybrid approaches. We combined collaborative and content-based filtering to build a hybrid movie recommendation system, MovieANN, based on neural network model. To make better recommendations in a collaborative approach, both user and movie clusters are formed. In addition to rating information, content information was also considered in the formation of the clusters. Clusters are formed according to K-Means and X-Means algorithms. Final clusters are chosen according to Davies-Bouldin Index and intra cluster distance. Homogeneity and density of the clusters are also considered. Movie and user clusters are mapped in the recommendation phase. The model is tested on a MoiveLens 1M dataset that consists of six thousand users, four thousand movies and one million ratings. Four clusters are formed to represent movie – user mappings and for each cluster, a recommendation model based on multi-layer neural network is constructed. The recommendation performance in terms of accuracy is 84.52%, 84.54% in terms of precision and 99.98% in terms of recall.

Özet

İnternetteki veri miktarı gün geçtikçe katlanarak artmaktadır. Kullanıcılar bu geniş veri okyanusunda sıklıkla kaybolmaktadır. Bu yüksek miktardaki ham veriden önemli bilgiyi filtrelemek için öneri sistemleri kullanılır. Bu sistemler işbirlikçi filtrelemeye, içeriğe dayalı filtrelemeye ve hibrit yaklaşımlara dayanmaktadır. Bu çalışmada yapay sinir ağına dayalı hibrit bir film öneri sistemi olan MovieANN, işbirlikçi ve içerik tabanlı filtreleme kullanılarak gerçekleştirilmiştir. İşbirlikçi bir yaklaşımla daha iyi öneriler yapmak için hem kullanıcı hem de film kümeleri oluşturulmuştur. Kümeler oluşturulurken rating bilgisine ek olarak içerik bilgisi de dikkate alınmıştır. Kümeleme için K-Means ve X-Means algoritmaları kullanılmıştır. Son kümeler, Davies-Bouldin Endeksi ve küme içi mesafelerine göre seçilir. Kümeler oluşturulurken homojenlik ve yoğunluk da göz önünde bulundurulmuştur. Öneri adımında film ve kullanıcı kümeleri eşleştirilir. İlgili model, altı bin kullanıcı, dört bin film ve bir milyon ratingden oluşan MoiveLens 1M veri kümesinde test edilmiştir. Film kullanıcı eşlemelerini temsil etmek için dört küme ve her küme için çok katmanlı sinir ağını temel alan bir öneri modeli oluşturulmuştur. Modelin öneri performansı doğruluk olarak % 84,52, kesinlik açısından % 84,54 ve geri çağırmada % 99,98'dir.

🔖

Cite This Article

YÜCEBAŞ, S. C. (2019). MovieANN: A Hybrid Approach to Movie Recommender Systems Using Multi Layer Artificial Neural Networks. Journal of Advanced Research in Natural and Applied Sciences, Cilt: 5 Sayı: 2, 214–232. https://ajindex.com/articles/907479

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (6)

  1. Attarde D.V., Singh M., 2017. Survey on Recommendation System Using Data Mining and Clustering Techniques. International Journal for Research in Engineering Application and Management (IJREAM), 3(9). ISSN: 2454-9150.
  2. Bobadilla J., Ortega F., Hernando A., Gutiérrez A., 2013. Recommender Systems Survey. Knowledge-Based Systems, 46: 109–132. Burke R., 2002. Hybrid recommender systems: Survey and experiments. User Model User Adapt Interact, 12: 331–370.
  3. Cami B. R., Hassanpour H., Mashayekhi H., 2017. A Content-Based Movie Recommender System Based on Temporal User Preferences. Third Iranian Conference on Intelligent Systems and Signal Processing (ICSPIS). DOI: 10.1109/ICSPIS.2017.8311601. Campos L.M, Fernández-Luna J.M., Huete J.F., Rueda-Morales M.A., 2010. Combining Content-Based and Collaborative Recommendations: A Hybrid Approach Based on Bayesian Networks. International Journal of Approximate Reasoning, 51: 785–799.
  4. Chen R., Hua Q., Chang Y.S., Wang B., Zhang L., Kong X.A, 2018. Survey of Collaborative Filtering-Based Recommender Systems: From Traditional Methods to Hybrid Methods Based On Social Networks. IEE Access. DOI: 10.1109/ACCESS.2018.2877208. Christakou C., Stafylopatis A., 2005. Hybrid Movie Recommender System Based on Neural Networks. Proceedings of the 5th International Conference on Intelligent Systems Design and Applications (ISDA’05). DOI: 10.1109/ISDA.2005.9. David D.L., Bouldin D.W., 1979. A Cluster Separation Measure. IEEE Transactions on Pattern Analysis and Machine Intelligence. PAMI-1(2): 224–227. DOI:10.1109/TPAMI.1979.4766909 Draisma J., Horobeţ E., Ottaviani G., Sturmfels B., Thomas R., 2014. The Euclidean Distance Degree. arXiv:1309.0049. Gupta U., Patil N., 2015. Recommender System Based On Hierarchical Clustering Algorithm Chameleon. IEEE International Advance Computing Conference (IACC). DOI: 10.1109/IADCC.2015.7154856. Harper M.F., Konstan J.A., 2015. The MovieLens Datasets: History and Context. ACM Transactions on Interactive Intelligent Systems (TiiS), 5(4). Haruna K., Ismail M. A., Damiasih D., Sutopo J., 2017. A Collaborative Approach for Research Paper. PloS One, 12(10): 1-17.
  5. Karimi, M., Jannach, D. & Jugovac, M.(2018). News recommender systems – Survey and roads ahead Information Processing & Management, 54(6): 1203-1227.
  6. Koohi H., Kiani K., 2017. A New Method To Find Neighbor Users That Improves The Performance Of Collaborative Filtering. Expert Systems with Applications: An International Journal, 83(C): 30-39. Kumar M