Related Entities Recommendation: A Review

Abstract

Background: In modern search engines, entity recommendation tries to improve users’ experience by assisting them in finding related entities for a given query. This concept has become an indispensable feature today. Actual web search engines have enriched their regular web search results by presenting related entities as recommendations for a user’s query. This new trend bridges the gap between two important domains: recommender systems and search engines. These two domains are increasingly coming back together. Studies on bridging these two popular systems vastly improve user’s experience when employing such hybrid system. Indeed, it is very intuitive to a user to get entities related to the entity appearing in its search query. This new task has attracted considerable interest. Methods: Many studies and works had been done to present this new concept. In this paper, we conduct a literature review of related entities recommender systems. We collect recently published papers in this field from journals and conferences. We used Google scholar library and summarize papers from different perspectives. Results: We investigate the proposed approaches by focusing on how they get benefit from contextual data and user’s feedback and how they utilize the knowledge graph for accurate recommendations. The principle when using knowledge bases like DBpedia or YAGO is that to retrieve a ranked list of related entities found in response to a main entity of the query, the system requires potential entities that can be considered as related and relevant to the main entity. These potential candidates can be obtained from the knowledge base. A comparison between approaches is provided and some future directions are presented. Conclusion: This review paper accomplished a summary of the literature and categorized and synthesized the papers according to different perceptions. To the best of our knowledge, this is the first review on related entities recommender systems using knowledge bases and user’s feedback