Content characterization (TC) gives a superior method to arrange data since it permits better comprehension and understanding of the substance. It manages the task of marks into a gathering of comparative printed record. Notwithstanding, TC inquire about for Asian language reports is generally restricted contrasted with English archives and much lesser especially for news articles. Besides, content characterization states to arrange printed archives in comparative morphology such Indonesian and Malay is yet uncommon.

Keywords : Content Characterization; News article; Text analysis; comments; structured classification