Auto-Summarization of Email Document Using Statistical Approach

In today’s world email communication is growing with fast rate. Thousands emails are coming into user inbox and he is not able to read each and every email documents. so users need such system by which they can classify and summarize emails. This paper discusses an email auto summarization system using statistical approach which uses vector space algorithm. It generates a summary for an email document from mail Inbox of email server. Our system is based on identification and extraction of important sentences from the input email document file. We listed a set of features that we collect as part of summary generation process. These features were stored using vector representation model. We defined a ranking function which ranks each sentence as a linear combination of the sentence features. We also discussed about techniques to achieve coherent and readable summaries of email message documents. The proposed system showed that the extraction based and position based email document summary generated is coherent the selected features are really helpful in extracting the important information from email documents. That generated summary will be displayed at client application interface. On that summary base we can classify emails. DOI: 10.17762/ijritcc2321-8169.15012