International Journal of Academic Research in Business and Social Sciences 2017, Vol. 7, No. 12 ISSN: 2222-6990 991 www.hrmars.com Ontology Population from Textual Document Sources for Environmental Management Domain based Lexical Patterns Technique Zaharudin Ibrahim, Tengku Adil Tengku Izhar, Mohd Sazili Shahibi, Mohd Ridwan Seman@ Kamarulzaman and Ahmad Zam Hariro Faculty of Information Management, Universiti Teknologi MARA, UiTM, Selangor, Malaysia DOI: 10.6007/IJARBSS/v7-i12/3729 URL: http://dx.doi.org/10.6007/IJARBSS/v7-i12/3729 Abstract This study focuses on the approach of identifying semantic relationships from unstructured textual documents related to river water pollution from websites and proposes a lexical pattern technique to acquire the instances. This study has identified 10 types of concepts (entities), 10 object properties (or semantic relations) and twenty lexico-syntactic patterns have been identified manually, including one from the Hearst hyponym rules. The lexical patterns have linked 45 terms that have the potential as instances. Based on this study, it is believed that determining the lexical pattern at an early stage is helpful in selecting relevant term from a wide collection of terms from the corpus. However, the relations and lexico-syntactic patterns or rules have to be verified by domain expert before employing the rules to the wider collection in an attempt to find more possible rules. This study shows that background knowledge about the domain is essential to develop the TBox ontology diagram that serve as backbone of the domain ontology. This diagram is essential as guideline in discovering lexico-syntactic patterns therefore expedite the knowledge extraction process. Keyword: Environmental Management, Lexical Patterns Technique, Ontology, Textual Document 1. Introduction First introduced by Aristotle, ontology has recently become a topic of interest in computer science. Ontology provides a shared understanding of the domain of interest to support communication among human and computer agents; it is typically represented in a machine processable representation language (Haase and Sure, 2004) and is also an explicit formal specification of terms, which represents the intended meaning of concepts, in the domain and relations among them, and considered as a crucial factor for the success of many knowledge-based applications (Staab, et al, 2001). With the overwhelming increase in biomedical literature in digital forms there is a need to extract knowledge from the literature (Fuller, et al, 2004). Ontology may also be helpful in fulfilling the need to uncover information present in large and unstructured bodies of text, commonly referred to as non-interactive literatures (Swanson & Smalheiser, 1997 ) i.e., literatures that do not cite each other but which, nevertheless, together present useful new information.