Movie Recommendation System Using k-clique and Association Rule Mining
Abstract
Various recommender systems have been presented in an effort to get better preciseness. In order to further improve more accuracy, the k-clique methodology, which is used to analyze social networks was introduced in the recommendation system and the result shows the k-clique method is effective in improving accuracy. In this paper, we propose a recommendation system using k-cliques and association rule mining with the best accuracy. To estimate the performance, the maximal clique method, collaborative filtering methods are monitored using the k nearest neighbors, the k-clique method, and the k-clique and association rule mining are used to evaluate the MovieLens data. The performance outputs show that the k-cliques and association rule mining get better the preciseness of the movie recommendation system than any other methods used in this experiment.
Keywords
Association rule mining Collaborative filtering using a k nearest neighbor k-cliques method Maximal clique method Movie recommendation systemNotes
Acknowledgments
This research was supported by the MSIP (Ministry of Science, ICT and Future Planning), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2018-2014-1-00720) supervised by the IITP (Institute for Information & communications Technology Promotion) and the National Research Foundation of Korea (No. NRF-2017R1A2B1008421).
References
- 1.Hao, F., Park, D.S., Pei, Z.: When social computing meets soft computing: opportunities and insights. Hum. Cen. Comput. Inf. Sci. 8(8), 1–21 (2018)Google Scholar
- 2.Hao, F., Sim, D.S., Park, D.S., Seo, H.S.: Similarity evaluation between graphs: a formal concept analysis approach. J. Inf. Process. Syst. 13(5), 1158–1167 (2017)Google Scholar
- 3.Hao, F., Park, D.S., Min, G., Jeong, Y.S., Park, J.H.: K-cliques mining in dynamic social networks based on triadic formal concept analysis. Neurocomputing 209, 57–66 (2016)CrossRefGoogle Scholar
- 4.Jeong, W.H., Kim, S.J., Park, D.S., Kwak, J.: Performance improvement of a movie recommendation system based on personal propensity and secure collaborative filtering. J. Inf. Process. Syst. 9(1), 157–172 (2013)CrossRefGoogle Scholar
- 5.Viana, P., Pinto, J.P.: A collaborative approach for semantic time-based video annotation using gamification. Hum. Cen. Comput. Inf. Sci. 7(13), 1–21 (2017)Google Scholar
- 6.Hao, F., Park, D.S., Pei, Z.: Detecting bases of maximal cliques in social networks. In: MUE2017, Seoul, Korea, p. 1 (2017)Google Scholar
- 7.Hao, F., Min, G., Pei, Z., Park, D.S., Yang, L.T.: K-clique communities detection in social networks based on formal concept analysis. IEEE Syst. J. 11, 250–259 (2015). https://doi.org/10.1109/jsyst.2433294CrossRefGoogle Scholar
- 8.Gregori, E., Lenzini, L., Mainardi, S.: Parallel (k)-clique community detection on large-scale networks. IEEE Tran. Parallel Distrib. Syst. 24(8), 1651–1660 (2013)CrossRefGoogle Scholar
- 9.Surbhi, K.S., Jalpa, T.P.: A survey on association rule mining. In: International Conference on Advanced Computing and Communication Technology, IEEE Conference, pp. 212–216 (2015)Google Scholar
- 10.Harper, F.M., Joseph, A.K.: The MovieLens datasets: history and context. ACM Trans. Interact. Intell. Syst. (TiiS) 5(4), 19 (2015). Article 19Google Scholar
- 11.Tofallis: A better measure of relative prediction accuracy for model selection and model estimation. J. Oper. Res. Soc. 66(8), 1352–1362 (2015)CrossRefGoogle Scholar
- 12.Hyndman, R.J., Anne, B.K.: Another look at measures of forecast accuracy. Int. J. Forecast. 22(4), 679–688 (2006)CrossRefGoogle Scholar
- 13.Kim, S., Kim, H.Y.: A new metric of absolute percentage error for intermittent demand forecasts. Int. J. Forecast. 32(3), 669–679 (2016)CrossRefGoogle Scholar