Galley Proof 23/10/2014; 17:09 File: his203.tex; BOKCTP/wyn p. 1 International Journal of Hybrid Intelligent Systems 00 (2014) 1–13 1 DOI 10.3233/HIS-140203 IOS Press Multiple developing news stories identified and tracked by social insects and visualized using the new galactic streams and concurrent streams metaphors Stefan Sabo ∗ , Alena Kovarova and Pavol Navrat Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia Abstract. We have developed an approach to identification and tracking of currently unfolding news stories extracted from the news articles published on the Web. Our approach employs a set of agents to retrieve those articles from the Web that might refer to some developing news story. The set of agents is inspired by social insects, in particular by a bee colony. Bees identify popular terms, referred to as story words, relevant to the ongoing news stories and use them in foraging articles. 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. Further we developed ways of visualization of multiple stories represented by sets of articles ordered in time. We propose two new metaphors both employing an exponential timeline. Both galactic streams and concurrent streams are highly suitable for visualizing multiple developing stories. Keywords: Beehive metaphor, community detection, news stories, social insect, bee hive, topic detection and tracking, visualisa- tion, galactic streams, concurrent streams 1. Introduction 1 Following of stories has become a part of our daily 2 routine. Whether it is current events worldwide, per- 3 sonally relevant events, or just daily weather, by fol- 4 lowing the development around us, we are gathering 5 information crucial for our daily decision-making. In 6 our work we focus on tracking of globally available 7 news stories. In our case, a story is not an article or a 8 report in a newspaper, but a set of content-related arti- 9 cles forming a storyline evolving over time. Our goal 10 * Corresponding author: Stefan Sabo, Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia. E-mail: stefan.sabo@stuba.sk. is to provide automated means of identifying and sub- 11 sequently tracking of interesting stories discussed in 12 news articles on the Web. While this is not a new idea, 13 we aim to achieve this by utilizing a set of independent 14 agents inspired by social insect. Every agent is capa- 15 ble of tracking a single aspect of a news story. By de- 16 ploying a group of such agents, we are able to establish 17 news stories, currently discussed in a set of articles and 18 continuously follow developments of stories dynam- 19 ically as they unfold. Our approach does not require 20 previous training or offline dataset analysis in order 21 to identify discussed news stories, as no single agent 22 holds any aggregate knowledge of story structure. In- 23 stead, each agent holds only a single term related to the 24 stories and the final story structure is obtained through 25 1448-5869/14/$27.50 c  2014 – IOS Press. All rights reserved