In information retrieval, relevance is perceived as a multidimensional and dynamic concept influenced by user, task, and domain factors. Relying on this perspective, researchers have introduced multidimensional relevance models addressing diverse search tasks across numerous knowledge domains. Through our systematic review of 72 studies, we categorize research based on domain specificity and the distinct relevance aspects employed for estimating multidimensional relevance. Moreover, we highlight the approaches used to aggregate scores related to these factors and rank information items. Our insights underline the importance of concise definitions and unified methods for estimating relevance factors within and across domains. Finally, we identify benchmark collections for evaluations based on multiple relevance aspects while underscoring the necessity for new ones. Our findings suggest that large language models hold considerable promise for shaping future research in this field, mainly due to their relevance labeling abilities.This article is categorized under:
Application Areas > Science and Technology
Technologies > Computational Intelligence