<![CDATA[In recent years, ontologies have received a lot of attention as a knowledge representation technique. Constructing an ontology can be a difficult task for several reasons: it necessitates time-consuming expert work, the classification task is not as simple as it appears, and the incredible speed with which knowledge evolves in the real world forces ontology engineers to constantly update and enrich the generated ontologies with new concepts, terms, and lexicon. However, there are other ways to automate ontology construction, such as semi-automatically, where human intervention is required in one or more ontology design tasks, and fully automatically, where the entire ontology construction is delegated to a software system. In this paper, we will conduct a systematic review of literature that will focus on a comparative analysis of different techniques relating to both semi-automatic and fully automatic ontology construction using various techniques and automated algorithms applied. In these fields, the goal is to identify the domain areas, current trends, data architectures, and ongoing challenges. This paper will review academic documents published in peer-reviewed venues from 2017 to 2021, based on a four-step selection process of identification, screening, eligibility, and inclusion for the selection process. To examine these documents, a systematic review was conducted and six main research questions were answered. The results indicate that automatic ontology construction could give higher complexity, shorter time, and reduce the role of the expert knowledge to evaluate ontology than manual ontology construction. The fields that have been investigated in this survey include online retail, biomedical, public security, information security (IS), Quran, Arabic, Dubai government services, Alzheimer’s disease, agriculture, Chinese tax, job portal, sentiment, and ontology learning. Finally, we summarize the most commonly used methods in automatic ontology construction, which we believe will serve as a foundation for future multidisciplinary research.]]>
