Text mining for science and technology: citation and discovery

This paper addresses 3 complementary components of text mining: Citation scientometrics, seminal literature reviews, and literature-related discovery and innovation.

By Gregory Piatetsky, Jul 31, 2013.

The following paper would be interesting to many KDnuggets readers who want to learn more about text mining, especially in science and technology.

Journal of Scientometric ResearchText mining for science and technology - a review part 2 - citation and discovery, by Ronald N. Kostoff, a Research Affiliate with the School of Public Policy and STIP, was published in the Journal of Scientometric Research [1].

This article is the second part of a two-part review of Dr. Kostoff work in developing text mining procedures. Part 2 addresses three complementary components of text mining:

  • Citation scientometrics,
  • seminal literature reviews (SLR),
  • and literature-related discovery and innovation (LRDI).

All three have at their core the development of very comprehensive and precise queries for retrieving the data of interest. For any literature of interest, the citation scientometrics approach analyzes in detail the papers that cite the literature of interest (citation mining), and/or the papers that are cited by the literature of interest.

The SLR uses the highly-cited references in a retrieved literature of interest to map out the intellectual heritage of that literature. The LRDI integrates (a) discovery generation from disparate literatures with (b) the wealth of knowledge contained in the prior art to (c) potentially solve technical problems that appear intractable. The review highlights each of the approaches drawing from studies undertaken by the author and his research group.

The article can be accessed online at www.jscires.org/text.asp?2013/2/1/3/115862.

[1] Kostoff RN. Text mining for science and technology: A review - Part II-citation and discovery. J Sci Res 2013;2:3-14.