Enhancing Decision Making with Semantic-Based Hybrid Recommender System

Decision making can be a complex and challenging task, particularly in the context of an overwhelming amount of information available on the web. Recommender systems have emerged as a solution to aid decision making by suggesting relevant items based on users' preferences and needs. However, traditional content-based recommender systems have been criticized for their lack of diversity in recommendations. On the other hand, collaborative filtering suffers from scalability issues due to the high computational complexity of similarity calculations for large datasets. To overcome these limitations, we propose a hybrid recommender system that leverages Linked Open Data and Ant Colony Optimization. Our approach utilizes semantic databases to improve the precision of recommendations and ACO algorithm to optimize the selection of diverse items. Experimental results demonstrate that our proposed system outperforms traditional recommendation systems in terms of decision aid and provides users with personalized and diverse recommendations. This research can contribute to the development of decision aid applications and improve the quality of decision making.