A hybrid recommender system based on data enrichment on the ontology modelling

Abstract

Background: A recommender system captures the user preferences and behaviour to provide a relevant recommendation to the user. In a hybrid model-based recommender system, it requires a pre-trained data model to generate recommendations for a user. Ontology helps to represent the semantic information and relationships to model the expressivity and linkage among the data. Methods: We enhanced the matrix factorization model accuracy by utilizing ontology to enrich the information of the user-item matrix by integrating the item-based and user-based collaborative filtering techniques. In particular, the combination of enriched data, which consists of semantic similarity together with rating pattern, will help to reduce the cold start problem in the model-based recommender system. When the new user or item first coming into the system, we have the user demographic or item profile that linked to our ontology. Thus, semantic similarity can be calculated during the item-based and user-based collaborating filtering process. The item-based and user-based filtering process are used to predict the unknown rating of the original matrix. Results: Experimental evaluations have been carried out on the MovieLens 100k dataset to demonstrate the accuracy rate of our proposed approach as compared to the baseline method using (i) Singular Value Decomposition (SVD) and (ii) combination of item-based collaborative filtering technique with SVD. Experimental results demonstrated that our proposed method has reduced the data sparsity from 0.9542% to 0.8435%. In addition, it also indicated that our proposed method has achieved better accuracy with Root Mean Square Error (RMSE) of 0.9298, as compared to the baseline method (RMSE: 0.9642) and the existing method (RMSE: 0.9492). Conclusions: Our proposed method enhanced the dataset information by integrating user-based and item-based collaborative filtering techniques. The experiment results shows that our system has reduced the data sparsity and has better accuracy as compared to baseline method and existing method.

A hybrid recommender system based on description/dialetheic logic and linked data

“…When comparing the papers with respect to their metrics, our work outperforms all the papers by a wide range, with the exception of (Selvan et al, 2019), where our work is better in the Precision metric and inferior in the Recall and F 1‐measure metrics, but it can also be observed that these difference are minimal. It is also important to highlight that there is no previous work that evaluates the quality of the generated ontology (see works, Chew et al, 2021; Mahdi & Hadi, 2021; Selvan et al, 2019), only McSherry (2006) and our work proposes a metric to evaluate it (completeness).…”

“…They use a social LD platform to design a fully decentralized and privacy‐aware platform that supports interoperability and care integration. Chew et al (2021) define a hybrid model‐based recommender system, which is pre‐trained with data to generate recommendations for a user using an ontology that helps to represent the semantic information and relationships to model the expressivity and linkage among the data. They define a matrix factorization model accuracy by utilizing the ontology to enrich the information of the user‐item matrix by integrating the item‐based and user‐based collaborative filtering techniques.…”

An e-Learning Recommendation System Framework

“…3) Hybrid Filtering Technique: Real-world recommender systems usually combine the best features among several recommendation techniques into a hybrid technique to increase performance and overcome limitations in each technique. Based on the hybrid techniques, the advantages of one algorithm might be outweighed by the disadvantages of another algorithm, resulting in better suggestions than those provided by a single algorithm [21]. Multiple recommendation approaches can be employed to conceal the flaws of each individual recommendation strategy in a combined model.…”