A New Semantic Similarity Measure Based On Ontology for Movie Rate Prediction
Vandana Mohan Patil1, J. B. Patil2
1Vandana Mohan Patil, Department of Computer Engineering, SES’s R.C.Patel Institute of Technology, Shirpur Dist. Dhule, India.
2Prof. Dr. J. B. Patil, Department of Computer Engineering, SES’s R.C.Patel Institute of Technology, Shirpur Dist. Dhule, India.
Manuscript received on 07 August 2019. | Revised Manuscript received on 15 August 2019. | Manuscript published on 30 September 2019. | PP: 6756-6762 | Volume-8 Issue-3 September 2019 | Retrieval Number: C4442098319/19©BEIESP | DOI: 10.35940/ijrte.C4442.098319
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A recommendation algorithm comprises of two important steps: 1) Predicting rates, and 2) Recommendation. Rate prediction is a cumulative function of the similarity score between two movies and rate history of those movies by other users. There are various methods for rate prediction such as weighted sum method, regression, deviation based etc. All these methods rely on finding similar items to the items previously viewed/rated by target user, with assumption that user tends to have similar rating for similar items. Computing the similarities can be done using various similarity measures such as Euclidian Distance, Cosine Similarity, Adjusted Cosine Similarity, Pearson Correlation, Jaccard Similarity etc. All of these well-known approaches calculate similarity score between two movies using simple rating based data. Hence, such similarity measures could not accurately model rating behavior of user. In this paper, we will show that the accuracy in rate prediction can be enhanced by incorporating ontological domain knowledge in similarity computation. This paper introduces a new ontological semantic similarity measure between two movies. For experimental evaluation, the performance of proposed approach is compared with two existing approaches: 1) Adjusted Cosine Similarity (ACS), and 2) Weighted Slope One (WSO) algorithm, in terms of two performance measures: 1) Execution time and 2) Mean Absolute Error (MAE). The open-source Movielens (ml-1m) dataset is used for experimental evaluation. As our results show, the ontological semantic similarity measure enhances the performance of rate prediction as compared to the existing-well known approaches.
Keywords: Ontology, Recommendation, Rate Prediction, Semantic Similarity Measure.
Scope of the Article: Regression and Prediction