Content words extraction using Malay text document / Nurfarahidayu Samshudin

Information is growing rapidly; anyone is able to get the information easily without any restriction especially using the World Wide Web. However, cause of too many information, sometimes readers cannot get the important value of that information. Therefore, it will leads to wrong information and waste of time on reading. The research proposes an algorithm that will automatically extract the Malay documents to improve access to information. Content words extraction techniques is explored and used as possible content and value for the text document. In the process of development the prototype, Bigram technique is introduce to assists on searching the related word of content word. As a result, the prototype will display all related sentences with content words.