Social insect inspired approach for identification and dynamic tracking of news stories on the Web

In this paper we present an approach to identification and tracking of currently unfolding news stories extracted from the news articles published on the Web. Our approach utilizes a set of social insect inspired agents to retrieve articles from the Web and identify popular terms, referred to as story words, relevant to the ongoing news stories. This allows for a dynamic approach that reflects the changes in article space as new stories unfold and new articles are added. Subsequently a graph representation of the article space is constructed, that contains retrieved articles and identified story words interconnected by edges according to relationships of relevance identified between elements of the graph. Stories are then extracted from the constructed graph by using Louvain method, commonly used to identify communities within modular graphs. Using this approach we have been able to identify news stories in a stream of articles retrieved from the Web with precision of 75.56%, with best precision generally achieved for recent news stories described by popular story words.