The keyword extraction refers to the process of extracting the essential words which reflect the entire content from an article. In this research, the keyword extraction is viewed into a binary classification where each word is classified into one of the two categories: ’keyword’, or ’non-keyword’. We
prepare sample words which are labeled with one of the two categories and encode them into their structured forms. By learning the sample words, we built the classification capacity,encode novice words into the structured forms, and classify them into one of the two categories. In this research, we use a supervised learning algorithm for the task which is viewed into the classification task.