Abstract:
In the stages of pre-writing and writing of a news article, journalists require to process the gathered data to identify important points and events which will predominantly support the main theme of the news story. In relation to the field of computer science, there is a lack of intelligent systems to help organize unstructured journalist data and optimize the news data pre-processing stage. There are existing research projects in the area of natural language processing which are focusing on text ordering and main theme identification of textual documents. However, there is no system, which is fine-tuned for the journalism domain, that can utilize the main theme of an unstructured textual document (journalistic notes) to semantically organize and prioritize text.
