Key points are not available for this paper at this time.
Currently, unstructured textual data analysis has attracted researchers' interest because it offers valuable information into many fields such as business, education, political, healthcare, crime prevention and other. Various sources are accessible that contain unstructured textual data such as online documents, Facebook, Twitter or Instagram. However, the implementation process for these types of unstructured data is limited, especially for Malay language. The lack of textual analysis process brings difficulties in obtaining important information for decision-making. This paper presented an Automated Malay Named Entity Recognition (AMNER) conceptual model using conditional random fields method for Malay language to recognize entities from unstructured textual data. The analysis focused on the developmental model based on Malay language features which guided the recognition process of entities from unstructured text documents.
Salleh et al. (Mon,) studied this question.