ABSTRACT
Recommender system is an effective tool to avoid amount of useless information given large-scale websites, which has achieved commercial success. Existing recommendation methods can be roughly divided into the content based filtering and collaborative filtering, and the latter one actually takes advantage of collective intelligence and is particularly popular because of its flexibility and independence of the item content description. Despite its popularity, there are at least two disadvantages with the collaborative filtering, respectively about the diversity of interest points and cold start. In this paper, a knowledge network system is introduced into the recommender system, which can be formed by collective intelligence in an evolutional way. Also using the collective intelligence, the proposed method is able to tackle or relieve the above disadvantages of the collaborative filtering. Specifically, it is able to recommend to users the closely related items based on an inherent interest structure and push items with diverse interest points. And by including a multi-round voting mechanism in the evolutional collective intelligence algorithm, the accumulation requirement of new records is reduced. Two more benefits with the proposed method are respectively the higher recommendation accuracy also based on the above mentioned multi-round voting mechanism, and the generalizable knowledge structure automatically extracted in the evolutional process. Explanative comparison with the collaborative filtering is made, and finally experimental comparison witnesses the efficacy of the proposed method.
- Adomavicius, G., Tuzhilin, A.: Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge & Data Engineering (6), 734--749 (2005)Google ScholarDigital Library
- Barragáns-Martínez, A.B., Costa-Montenegro, E., Burguillo, J.C., Rey-López, M., Mikic-Fonte, F.A., Peleteiro, A.: A hybrid content-based and item-based collaborative filtering approach to recommend tv programs enhanced with singular value decomposition. Information Sciences 180(22), 4290--4311 (2010)Google ScholarDigital Library
- Bernardis, C., Ferrari Dacrema, M., Cremonesi, P.: A novel graph-based model for hybrid recommendations in cold-start scenarios. In: Late-Breaking Results Track Part of the Twelfth ACM Conference on Recommender Systems (2018)Google Scholar
- Bobadilla, J., Ortega, F., Hernando, A., Bernal, J.: A collaborative filtering approach to mitigate the new user cold start problem. Knowledge-Based Systems 26, 225--238 (2012)Google ScholarDigital Library
- Chowdhury, S.R., Rodríguez, C., Daniel, F., Casati, F.: Wisdom-aware computing: on the interactive recommendation of composition knowledge. In: International Conference on Service-Oriented Computing. pp. 144--155. Springer (2010)Google Scholar
- Falk, K.: Practical Recommender Systems. Manning Publications (2019)Google Scholar
- Lee, S.K., Cho, Y.H., Kim, S.H.: Collaborative filtering with ordinal scale-based implicit ratings for mobile music recommendations. Information Sciences 180(11), 2142--2155 (2010)Google ScholarDigital Library
- Lika, B., Kolomvatsos, K., Hadjiefthymiades, S.: Facing the cold start problem in recommender systems. Expert Systems with Applications 41(4), 2065--2073 (2014)Google ScholarDigital Library
- Liu, J., Dolan, P., Pedersen, E.R.: Personalized news recommendation based on click behavior. In: Proceedings of the 15th international conference on Intelligent user interfaces. pp. 31--40. ACM (2010)Google ScholarDigital Library
- Nilashi, M., Ibrahim, O., Bagherifard, K.: A recommender system based on collaborative filtering using ontology and dimensionality reduction techniques. Expert Systems with Applications 92, 507--520 (2018)Google ScholarDigital Library
- Ortega, F., Rojo, D., Valdiviezo-Díaz, P., Raya, L.: Hybrid collaborative filtering based on users rating behavior. IEEE Access 6, 69582--69591 (2018)Google ScholarCross Ref
- Starbird, K., Muzny, G., Palen, L.: Learning from the crowd: collaborative filtering techniques for identifying on-the-ground twitterers during mass disruptions. In: Proceedings of 9th International Conference on Information Systems for Crisis Response and Management, ISCRAM. pp. 1-10 (2012)Google Scholar
- Su, X., Khoshgoftaar, T.M.: A survey of collaborative filtering techniques. Advances in artificial intelligence (Article ID 421425), 19 pages (2009)Google Scholar
- Thakkar, P., Varma, K., Ukani, V., Mankad, S., Tanwar, S.: Combining user-based and item-based collaborative filtering using machine learning. In: Information and Communication Technology for Intelligent Systems, pp. 173--180. Springer (2019)Google Scholar
- Xiang, T., Huang, Z., Bai, P., Ji, C., Liu, Z.: Knowledge network system (KNS) by evolutionary collective intelligence (ECI): Model, algorithm and applications. Technical Report, arXiv preprint arXiv:1906.07358 (2019)Google Scholar
Index Terms
- Comparison between Knowledge Network System and Collaborative Filtering in Recommender System
Recommendations
Improving Accuracy of Recommender System by Item Clustering
Recommender System (RS) predicts user's ratings towards items, and then recommends highly-predicted items to user. In recent years, RS has been playing more and more important role in the agent research field. There have been a great deal of researches ...
CoDFi-DL: a hybrid recommender system combining enhanced collaborative and demographic filtering based on deep learning
AbstractThe cold start problem has always been a major challenge for recommender systems. It arises when the system lacks rating records for new users or items. Addressing the challenge of providing personalized recommendations in the cold start scenario ...
Collaborative Filtering for Recommender Systems
CBD '14: Proceedings of the 2014 Second International Conference on Advanced Cloud and Big DataCollaborative filtering (CF) predicts user preferences in item selection based on the known user ratings of items. As one of the most common approach to recommender systems, CF has been proved to be effective for solving the information overload ...
Comments