2012

Bir İçerik-Tabanlı Ürün Öneri Yaklaşımı

Bu çalışmada, bir içerik-tabanlı öneri yaklaşımı önerilmektedir. Bu yaklaşım, IMDB’nin ön işlenmiş 245 en iyi film özetlerini ve anket yöntemiyle ortaya çıkan kullanıcının favori film türlerini kullanmakta ve daha sonra, -bir ürün havuzundan- kullanıcının “beğenebileceği” potansiyelde ürünleri önermektedir. Test için; Amazon.com’dan gerçek ürünleri içeren bir test veri seti yaratılmıştır, ve önerilen yaklaşımı kullanan ve kullanıcıları bu yaklaşımın sonuçlarını değerlendirmek için yönlendiren bir Web uygulaması tasarlanıp geliştirilmiştir. 52 gönüllü denek teste katılmıştır. Denek, görüntülenen 10 ürünün her birini ayrı ayrı incelemiş ve derecelendirmiştir. Derecelendirme, “Hiç” (%0), “Biraz” (%25), “Orta” (%50), “Çok” (%75) ve “Son derece” (%100) olarak beş-seviyeli Likert-türü ölçüye dayalı yapılmıştır. Deneklerin ürünleri orta derecede beğendiğini söylemek mümkündür. Ürün değerlendirmeleri “beğenilen” ve “beğenilmeyen” olarak iki kategoride kategorize edildiğinde, deneklerin ürünlerin yaklaşık %78,65’ini beğendiğini söylemek mümkündür. Bu yaklaşım, kullanıcının “beğenebileceği” potansiyelde ürünler önermek için Amazon.com gibi e-ticaret uygulamalarına entegre olabilir.

Anahtar Kelimeler:

Öneri sistemleri, İçerik-tabanlı, Metin madenciliği, Bilgi filterleme, Bilgi erişim, E-ticaret

A Content Based Product Recommendation Approach

In this study, a content-based recommendation approach is proposed. It utilizes the preprocessed 245 top movie summaries of IMDB and the favorite movie genres of the user elicited with the questionnaire method and then, recommends potential products -from a product pool- that the user can “like”. For testing; a test dataset that consists of real products from Amazon.com was created, and a Web application that uses the proposed approach and leads the users to evaluate the results of this approach was designed and developed. 52 volunteered subjects attended the test. The subject examined and graded each of the 10 products displayed. Grading was based on the five-level Likert-type scale “Not at all” (0%), “Slightly” (25%), “Moderate” (50%), “Very” (75%), and “Extremely” (100%). It is possible to say that the subjects are moderately liked the products. When the product evaluations are categorized in two categories as “liked” and “disliked”, it is possible to say that the subjects liked ~78.65% of the products. This approach could be integrated into e-commerce applications like Amazon.com for recommending potential products that the user can “like”.

Keywords:

Recommendation systems, Content-based, Text mining, Information filtering, Information retrieval, E-commerce,

PDF

___

1. Son, J., Kim, S.B., 2017. Content-Based Filtering for Recommendation Systems Using Multiattribute Networks. Expert Systems with Applications, 89, 404-412. doi:10.1016/j.eswa.2017.08.008.
2. Pu, P., Chen, L., Hu R., 2011. A User-Centric Evaluation Framework for Recommender Systems. The 5th ACM Conference on Recommender Systems, Chicago, Illinois, USA, 157-164. doi: 10.1145/2043932.2043962.
3. Zihayat, M., Ayanso, A., Zhao, X., Davoudi, H., An, A., 2019. A Utility-Based News Recommendation System. Decision Support Systems, 117, 14-27. doi: 10.1016/j.dss.2018.12.001.
4. Ma, M., Na, S., Wang, H., Chen, C., Xu, J., 2021. The Graph-based Behavior-aware Recommendation for Interactive News. Applied Intelligence, 1573-7497. doi: 10.1007/s10489-021-02497-x.
5. Symeonidis, P., Kirjackaja, L., Zanker, M., 2021. Session-Based News Recommendations Using Simrank on Multi-modal Graphs. Expert Systems with Applications, 180, article no. 115028. doi: 10.1016/j.eswa.2021.115028.
6. Giabelli, A., Malandri, L., Mercorio, F., Mezzanzanica, M., Seveso, A., 2021. Skills2Job: A Recommender System that Encodes Job Offer Embeddings on Graph Databases. Applied Soft Computing, 101, article no. 107049. doi: 10.1016/j.asoc.2020.107049.
7. Yang, S., Korayem, M., Aljadda, K., Grainger, T., Natarajan, S., 2017. Combining Content-Based and Collaborative Filtering for Job Recommendation System: A Cost-Sensitive Statistical Relational Learning Approach. Knowledge-based Systems, 136, 37-45. doi: 10.1016/j.knosys.2017.08.017.
8. Chen, M.H., Teng, C.H., Chang, P.C., 2015. Applying Artificial Immune Systems to Collaborative Filtering for Movie Recommendation. Advanced Engineering Informatics, 29(4), 830-839. doi: 10.1016/j.aei.2015.04.005.
9. An, H., Kim, D., Lee, K., Moon, N., 2021. Movie DIRec: Drafted-input-based Recommendation System for Movies. Applied Sciences, 11(21), article no. 10412. doi: 10.3390/app112110412.
10. Reddy, S., Nalluri, S., Kunisetti, S., Ashok, S., Venkatesh, B., 2019. Content-based Movie Recommendation System Using Genre Correlation. In: Satapathy, S.C., Bhateja, V., Das, S. (eds) Smart Intelligent Computing and Applications. Smart Innovation, Systems and Technologies, 105, 391-397, Springer, Singapore. doi: 10.1007/978-981-13-1927-3_42.
11. Wang, D., Liang, Y., Xu, D., Feng, X., Guan, R., 2018. A Content-Based Recommender System for Computer Science Publications. Knowledge-Based Systems, 157, 1-9. doi: 10.1016/j.knosys.2018.05.001.
12. Kang, Y., Hou, A., Zhao, Z., Gan, D., 2021. A Hybrid Approach for Paper Recommendation. IEICE Transactions on Information and Systems, E104D(8), 1222-1231. doi: 10.1587/transinf.2020BDP0008.
13. Sassi, I.B., Yahia, S.B., Liiv, I., 2021. MORec: At the Crossroads of Context-aware and Multi-Criteria Decision Making for Online Music Recommendation. Expert Systems with Applications, 183, article no. 115375. doi: 10.1016/j.eswa.2021.115375.
14. Cruz, A.F.T., Coronel, A.D., 2020. Towards Developing a Content-based Recommendation System for Classical Music. In: Kim, K.J., Kim, H.-Y. (eds) Information Science and Applications. Lecture Notes in Electrical Engineering, 621, 451-462, Springer, Singapore. doi: 10.1007/978-981-15-1465-4_45.
15. Hwangbo, H., Kim, Y.S., Cha, K.J., 2018. Recommendation System Development for Fashion Retail E-commerce. Electronic Commerce Research and Applications, 28, 94-101. doi: 10.1016/j.elerap.2018.01.012.
16. Pazzani, M.J., Billsus, D.J., 2007. Content-Based Recommendation Systems. In: Brusilovsky, P., Kobsa, A., Nejdl, W. (eds) The Adaptive Web. Lecture Notes in Computer Science, 4321, 325-341, Springer, Berlin, Heidelberg. doi: 10.1007/978-3-540-72079-9_10.
17. Guo, Y., Wang, M., Li, X., 2017. Application of an Improved Apriori Algorithm in a Mobile E-commerce Recommendation System. Industrial Management & Data Systems, 117(2), 287-303. doi: 10.1108/imds-03-2016-0094.
18. Sabitha, R., Vaishnavi, S., Karthik, S., Bhavadharini, R.M., 2022. User Interaction Based Recommender System Using Machine Learning. Intelligent Automation and Soft Computing, 31(2), 1037-1049. doi: 10.32604/iasc.2022.018985.
19. Zhang, Y., 2021. The Application of E-commerce Recommendation System in Smart Cities Based on Big Data and Cloud Computing. Computer Science and Information Systems, 18(4), 1359-1378. doi: 10.2298/CSIS200917026Z.
20. Gwadabe, T.R., Liu, Y., 2022. Improving Graph Neural Network for Session-based Recommendation System via Non-sequential Interactions. Neurocomputing, 468, 111-122. doi: 10.1016/j.neucom.2021.10.034.
21. Kottage, G.N., Jayathilake, D.K., Chankuma, K.C., Ganegoda, G.U., Sandanayake, T., 2018. Preference Based Recommendation System for Apparel E-commerce Sites. IEEE/ACIS 17th International Conference on Computer and Information Science, Singapore, 122-127. doi: 10.1109/icis.2018.8466382.
22. Zhou, N., Tian, J., Li, M., 2021. Online Recommendation Based on Incremental-input Self-organizing Map. Electronic Commerce Research and Applications, 50, article no. 101096. doi: 10.1016/j.elerap.2021.101096.
23. Zheng, J., Li, Q., Liao, J., 2021. Heterogeneous Type-specific Entity Representation Learning for Recommendations in E-commerce Network. Information Processing & Management, 58(5), article no. 102629. doi: 10.1016/j.ipm.2021.102629.
24. Porter, M., Boulton, R., The English (Porter2) Stemming Algorithm: English Stop Words List (UTF-8 Encoding), Snowball, Available at http://snowballstem.org/algorithms/english/stemmer.html - Access Date: 7 December 2018.
25. Měchura, M., Lemmatization-Lists: lemmatization-en.txt, Available at https://github.com/michmech/lemmatization-lists, Access Date: 8 December 2018.
26. Adomavicius, G., Tuzhilin, A., 2005. 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, 17(6), 734-749. doi:10.1109/TKDE.2005.99.
27. NlpTools, Available at http://php-nlp-tools.com, Access Date: 18 January 2019.
28. Isinkaye, F.O., Folajimi, Y.O., Ojokoh, B.A., 2015. Recommendation Systems: Principles, Methods and Evaluation. Egyptian Informatics Journal, 16(3), 261-273. doi: 10.1016/j.eij.2015.06.005.
29. Kramer, T., 2007. The Effect of Measurement Task Transparency on Preference Construction and Evaluations of Personalized Recommendations. Journal of Marketing Research, 44(2), 224-233. doi:10.1509/jmkr.44.2.224.