What's going on out there right now? A beehive based machine to give snapshot of the ongoing stories on the Web

Abstract

In this paper we present an approach, inspired by honey bees, that allows us to take a glance at current events by exploring a portion of the Web and extracting keywords, relevant to current news stories. Not unlike the bees, that cooperate together to retrieve little bits of food, our approach uses agents to select random keywords and carry them from one article to another, landing only on the articles relevant to the keyword. Keywords that best represent multiple articles are selected, while keywords not relevant to articles are subsequently discarded and not explored further. Our results show, that with this approach, it is possible to extract keywords relevant to news stories, without utilizing learning methods, or analysis of a data corpus.

Multiple developing news stories identified and tracked by social insects and visualized using the new galactic streams and concurrent streams metaphors

“…Subsequently, we present overview of our proposed method of story visualization. The task of story word extraction is a result of our previous work [22], therefore will be covered in less detail, mainly for reference. Along with the data acquisition task, we illustrate a proposed deployment scenario of our approach to dynamic identification and tracking of news stories, as they develop.…”

“…They are able to conform to a dynamically changing environment of news domain, without any prior knowledge of it. From the point of view of data acquisition, our agents are simple web crawlers that utilize swarm intelligence coordination mechanism in order to select new documents to be retrieved, as described in [22]. However, in contrast to our previous work that is focused on obtaining of static snapshots of currently discussed news stories, we have modified the approach for a continuous run, establishing a long term or even permanent presence of our agents over the Web, constantly re-evaluating and updating the set of current news stories.…”

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

“…The task of story word extraction is a result of our previous work [9], therefore will be covered in less detail, for reference. Along with the data acquisition task, we illustrate a proposed deployment scenario of our approach to dynamic identification and tracking of news stories, as they develop.…”

“…From the point of view of data acquisition, our agents are simple web crawlers, that utilize swarm intelligence coordination mechanism in order to select new documents to be retrieved, as described in [9]. However, in contrast to our previous work, that fo cused on obtaining of static snapshots of currently discussed news stories, we have modified the approach for continuous run, establishing a long term, or even permanent presence of our agents over the Web , constantly re-evaluating and updating the set of current news stories.…”

“…The basis of the story word extraction mechanism was given in our previous work [9], therefore we will give only a short review of it and point out the contributions, that have been made. The aim of story word extraction is to identify terms conunon for multiple articles, that indicate relevance of the given articles to a certain news story.…”