Presentation an Algorithm to Discover Association Rules from Text

In many situations, individuals or groups of individuals are faced with the need to examine sets of documents to achieve understanding of their structure and to locate relevant information. A handful of text data mining approaches are available to extract many potential information and association from large amount of text data. In general, data mining deals with structured data (for example relational databases), whereas text presents special characteristics and is unstructured. The unstructured data is totally different from databases, where mining techniques are usually applied and structured data is managed. Text mining can work with unstructured or semi structured data sets.In that context, this paper presents an algorithm to discover association rules from text. Our approach starts by building a relational database from the text data set. On top of that, a novel technique is presented that searching and recognize patterns in text, then extract association rules. Results have shown remarkable care and the efficiency of the proposed algorithm in comparison with the other methods.

Keywords:

Text Mining , Natural Processing Language , Association Rule Mining , Knowledge Discovery from Database , Detection Text Patterns