A tool for OLAP (On-Line Analytical Processing) on text documents

We want to automate the process of summarizing a collection of documents, and get an overall picture of the topics covered by the document collection. The summarized results should be easy to understand with simple visualization and able to get more details on selected topics by performing various operations. The purpose is to help users to save time on finding out interesting articles, and focus only on useful articles and conduct further analysis as they desire. In order to achieve this goal, we developed the tool Docs Summarizer, where we introduced Online Analytical Processing (OLAP) into document set summarization. Our Tool can take a collection of documents as input, and apply analysis on them to generate a series of meaningful outputs. The outputs include a list of top k analysis level categories and a two-dimensional matrix chart. The users can do further exploration on the outputs by performing various operations.