Processing online news streams for large-scale semantic analysis

Abstract

While Internet has enabled us to access a vast amount of online news articles originating from thousands of different sources, the human capability to read all these articles has stayed rather constant. Usually, the publishing industry takes over the role of filtering this enormous amount of information and presenting it in an appropriate way to the group of their subscribers. In this paper, the semantic analysis of such news streams is discussed by introducing a system that streams online news collected by the Europe Media Monitor to our proposed semantic news analysis system. Thereby, we describe in detail the emerging challenges and the corresponding engineering solutions to process incoming articles close to real-time. To demonstrate the use of our system, the case studies show a) temporal analysis of entities, such as institutions or persons, and b) their co-occurence in news articles.

Text visualization techniques: Taxonomy, visual survey, and community insights

“…Here, we list the categories with some references to prominent examples. Data sources include the following self-evident items: Document [33], Corpora [25], and Streams [19]. The special data properties include Geospatial [11], Timeseries [14], and…”

Feature-Based Visual Sentiment Analysis of Text Document Streams

“…So-called History Flows are used by Viégas et al [2004] to track collaborative authoring. Krstajic et al [2010] visualize daily aggregates of entity occurrences in news with stacked time series.…”

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

“…Such representation is appropriate rather for professionals. Krstajic et al [20] used a similar way of visualization, but instead of visualizing theme streams, they visualized streams of entities (an organisation or a person) and their relative share within news articles over a time period using a linear time scale.…”

“…), but more often the time dimension is visualized using a timeline oriented from left to right (as with ThemeRiver TM [19] or work of Krstajic et al [20]). Such timeline forms the base of our visualization model as well.…”