Using Text Mining Techniques in Electronic Data Interchange Environment

The internet is a huge source of documents, containing a massive number of texts in multilingual languages on a wide range of topics. These texts are demonstrating in an electronic documents format hosted on the web. The documents exchanged using special forms in an Electronic Data Interchange (EDI) environment. Using web text mining approaches to mine documents in EDI environment could be new challenging guidelines in web text mining. Applying text-mining approaches to discover knowledge previously unknown patters retrieved from the web documents by using partitioned cluster analysis methods such as kmeans methods using Euclidean distance measure algorithm for EDI text document datasets is unique area of research these days. Our experiments utilize the standard K-means algorithm on EDI text documents dataset that most commonly used in electronic interchange and we report some results using text mining clustering application solution called WEKA. This study will provide high quality services to any organization that is willing to use the system. Key-Words: Electronic Data Interchange (EDI), Web Mining, Text Mining, Clustering, Kmean algorithm, Similarity Measures, Partitioned Cluster Analysis.