Text Mining
Today, researchers have available to them a wealth of information from various data sources. Integrating these to form a coherent picture is a time-consuming task that keeps researchers away from their core activities. To address this need, Strand has developed its text mining technology called Grammatica.
Grammatica is Strand's text mining engine that enables you to extract key concepts, sentiments, and relationships from textual or "unstructured" data and convert them to a structured format that can be used to create predictive models. In the life sciences domain, Strand has applied Grammatica to extracting facts reported in scientific literature and in business intelligence domain to extract consumer sentiments and competitive intelligence data.
Grammatica's application to scientific literature helps researchers to uncover the interrelated roles of various genes, proteins and chemical reactions in cells and organisms, rather than looking at individual data sources in isolation. Such data extracted by Grammatica and the Grammatica engine itself are available in the GeneSpring® product.
In the business intelligence domain, Grammatica has been applied to two problems. The first one is the area of market research for analysing consumer sentiments expressed in various online blogs and community sites or ‘buzz analytics'. Second, Grammatica has been applied to mine facts relevant to competitive intelligence from various sources like press releases, company/market reports, internal research compilations, email exhanges, etc.
Grammatica is integrated with Strand's proprietary data mining platform - AVADIS®
Case Studies