Text Mining Through Semi Automatic Semantic Annotation

Abstract

The Web is the greatest information source in human history.Unfortunately, mining knowledge out of this source is a laboriousand errorpronetask. Many researchers believe that a solution to the problem canbefounded on semantic annotations that need to be inserted in web-baseddocuments and guide information extraction and knowledge mining. Inthispaper, we further elaborate a tool-supported process for semanticannotation ofdocuments based on techniques and technologies traditionally usedin softwareanalysis and reverse engineering for large-scale legacy code bases.Theoutcomes of the paper include an experimental evaluation frameworkandempirical results based on two case studies adopted from the Tourismsector.The conclusions suggest that our approach can facilitate the semi-automaticannotation of large document bases.