News analytics refers to the measurement of the various qualitative and quantitative attributes of textual news stories. Some of these attributes are: sentiment, relevance, and novelty. As methods, news analytics typically deploys automated text analysis using elements from natural language processing and machine learning such as latent semantic analysis, support vector machines, "bag of words" among other techniques.
This website focuses on the analysis of corporate news streams, one of the most common data sources used for news analytics. It provides a set of research apps that allow to text analyze the full sequence of firms' press releases throughout time - along different dimensions, such as sentiment, action types, or action patterns. Previously, this or comparable capabilities have been used for the following research purposes: (1) The scientific analysis of qualitative dimensions of event types that have previously been ignored by scholars. (2) The repeated longitudinal analysis and comparison of organizational behaviors. (3) Within business, news analytics informs event-driven trading strategies and business intelligence applications.
Our research apps can perform large scale analyses with many thousand press releases, making them suitable for academic studies that involve large samples of firms over extended time periods. They fill a capability gap at the individual researcher, which has been presumed to hold back innovative event-driven research: "But what's lacking, mostly, is a recognition that we actually need to have an event-driven research process to construct an evolutionary explanation with data, which means having information about the successive states of whatever it is we're observing, whatever the unit might be - teams, groups, organizations, or populations - and we need to have repeated measurements over a long period of time" (Murmann et. al, 2003: 12).
Figure 1: EventStudyTools' News Analytics Framework
Video 1: Bloomberg's View on News Analytics in Finance