Semantic relatedness (SR) is a form of measurement that quantitatively identifiesthe relationship between two words or concepts based on the similarity orcloseness of their meaning. In the recent years, there have been noteworthyefforts to compute SR between pairs of words or concepts by exploiting variousknowledge resources such as linguistically structured (e.g. WordNet) andcollaboratively developed knowledge bases (e.g. Wikipedia), among others. Theexisting approaches rely on different methods for utilizing these knowledgeresources, for instance, methods that depend on the path between two words, or avector representation of the word descriptions. The purpose of this paper is toreview and present the state of the art in SR research through a hierarchicalframework. The dimensions of the proposed framework cover three main aspects ofSR approaches including the resources they rely on, the computational methodsapplied on the resources for developing a relatedness metric, and the evaluationmodels that are used for measuring their effectiveness. We have selected 14representative SR approaches to be analyzed using our framework. We compare andcritically review each of them through the dimensions of our framework, thus,identifying strengths and weaknesses of each approach. In addition, we provideguidelines for researchers and practitioners on how to select the most relevantSR method for their purpose. Finally, based on the comparative analysis of thereviewed relatedness measures, we identify existing challenges and potentiallyvaluable future research directions in this domain.