Indonesia Conference Directory

The first step that is always passed by documents in natural language processing is preprocessing text. These steps are needed for transferring text from human language to machine-readable format for further processing. However, not many special applications have been found that function as text preprocessing. This has led to any research on natural language processing having to create its own program code for the preprocessing text phase. The main focus of this research is to create an integrated text preprocessing application that can be accessed by any researcher who needs it. Several issues discussed in this study include the design, implementation, testing and integration of each text preprocessing feature. Text preprocessing which is integrated in this research includes case folding, tokenizing, stop word removal and stemming. The tools used in this research are the NLTK library of python and Django framework.