Visual analysis of news streams with article threads

Abstract

The analysis of large quantities of news is an emerging area in the field of data analysis and visualization. International agencies collect thousands of news every day from a large number of sources and making sense of them is becoming increasingly complex due to the rate of the incoming news, as well as the inherent complexity of analyzing large quantities of evolving text corpora. Current visual techniques that deal with temporal evolution of such complex datasets, together with research efforts in related domains like text mining and topic detection and tracking, represent early attempts to understand, gain insight and make sense of these data. Despite these initial propositions, there is still a lack of techniques dealing directly with the problem of visualizing news streams in a "on-line" fashion, that is, in a way that the evolution of news can be monitored in real-time by the operator. In this paper we propose a purely visual technique that permits to see the evolution of news in real-time. The technique permits to show the stream of news as they enter into the system as well as a series of important threads which are computed on the fly. By merging single articles into threads, the technique permits to offload the visualization and retain only the most relevant information. The proposed technique is applied to the visualization of news streams generated by a news aggregation system that monitors over 4000 sites from 1600 key news portals worldwide and retrieves over 80000 reports per day in 43 languages.

Human Factors in Streaming Data Analysis: Challenges and Opportunities for Information Visualization

“…Matrices and heatmaps [CLS*12, Riv14, LB14, KBMK10] are used to reveal relationships between pairs of variables in multi‐dimensional data by mapping each variable to a spatial dimension to produce an image, and encoding the data at that point in the image with an appropriate colour. Though it is common for the encoded variables to be continuous, many cases also exist where variables are categorical, as occurs in combinatorial data analysis.…”

Story Tracker: Incremental visual text analytics of news story development

“…EventRiver 8 employs bubble-like visualization of news stories extracted from the broadcast news data, while CloudLines 9 uses kernel density estimation to visualize interesting episodes in irregular news time-series data. Real-time aggregation of news articles into important threads is presented by Krstajić et al 10 Aigner et al 11 recently provided an extensive systematic overview of time-oriented visualization techniques. In the field of visual analytics, the recently published TIARA 12 system integrates interaction methods with text summarization and visualization based on tag clouds and stacked graphs.…”

Dynamic Visual Analytics—Facing the Real-Time Challenge

“…In addition to that, they use LiveRAC and a spiral pixel visualization to interactively investigate streamed network traffic. Other domain-specific work focuses on near real-time visualization of online news [14]. The technique merges several articles into threads and uses categories to display the threads in a temporal colored line visualization.…”