„A project backed by a US intelligence agency might soon make it much easier to predict which technologies will one day become game-changers. Results revealed this week by the Intelligence Advanced Research Projects Activity (IARPA) suggest that clues in the wordings of, and relationships between, scientific papers and patents could foretell research successes.“
This passage from a recent Nature-piece nicely sums up the essence of FUSE – with the acronym standing for „Foresight and Understanding from Scientific Exposition“, a massive text-mining approach that ist intended to go beyond traditional content and scientific influence analyses.
„FUSE takes this further by mining millions of papers and patents in both English and Chinese, two of the most commonly used languages in scientific literature. (…) The analysis and indicators can predict whether a nascent field will become prominent or whether it is simply a source of excitement that will soon die out.“
One of the FUSE-teams uses software algorithms to analyse ‘sentiment’ in the natural language of papers. „For instance, authors might say that their work builds on or contradicts a cited paper, or use descriptive language that expresses excitement“ (Nature).
To get an idea, how FUSE will actually work, there is a niece little twist on this story on US intelligence analysis, as some principles for the programme actually might be traced back to soviet-era russian innovation researcher Genrich Altshuller, whose TRIZ-system is still influencing innovation processes and their evaluation today.
Indeed, interesting perspectives for extended intelligence analysis! For an open source overview of FUSE, have a look here: FUSE: concept and overview.