“Term clumping” for technical intelligence: A case study on dye-sensitized solar cells

Abstract

Tech Mining seeks to extract intelligence from Science, Technology & Innovation information record sets on a subject of interest. A key set of Tech Mining interests concerns which R&D activities are addressed in the publication and patent abstract records under study. This paper presents six "term clumping" steps that can clean and consolidate topical content in such text sources. It examines how each step changes the content, potentially to facilitate extraction of usable intelligence as the end goal. We illustrate for an emerging technology, dye-sensitized solar cells. In this case we were able to reduce some 90,980 terms & phrases to more user-friendly sets through the clumping steps as one indicator of success. The resulting phrases are better suited to contributing usable technical intelligence than the original results. We engaged seven persons knowledgeable about dye-sensitized solar cells (DSSCs) to assess the resulting content. These empirical results advanced the development of a semi-automated term clumping process that can enable extraction of topical content intelligence.

Semi-automatic Technology Roadmapping Composing Method for Multiple Science, Technology, and Innovation Data Incorporation

“…1) The clustering-based topic identification model -we group the term clumping process [20]-cleaned features of science data sources into "general feature" and "specific feature," and refine the data-oriented, but adaptive text clustering model [21] to identify the hot research topics and key technologies;…”

“…Therefore, our emphasis in this paper is science textual data, and text mining techniques will be used to handle the raw data for feature extraction. In [20], we developed a Term Clumping process to retrieve key terms from science textual data by term removal, consolidation, and clustering. However, the aim of the original Term Clumping is to remove common terms and select core terms; thus, we undertake modifications on this approach to meet our exact needs for feature extraction, to evolve it by adding a thesaurus for our specified technical domain, adjusting the existing Science and Academic Thesaurus, skipping the Term Frequency Inverse Document Frequency (TFIDF) approach for term removal, but applying it for feature weighting, and skipping the clustering-based term consolidation approaches (e.g., Term Clustering and Combine Term Network).…”

Identification of technology development trends based on subject–action–object analysis: The case of dye-sensitized solar cells

“…The researchers in our lab have built a thesaurus by the method of term clumping. This thesaurus can be used to process large amount of documents including treat the synonyms (Zhang et al, 2014a(Zhang et al, , 2014b. In addition, Choi et al (2011) also proposes such a method for this purpose.…”

Technology Analysis of Global Smart Light Emitting Diode (LED) Development Using Patent Data

“…Keller and Gracht (2014) also used a Delphi survey for technology forecasting analysis. In recent years, many studies have been conducted on a hybrid technology analysis that combines the results of qualitative and quantitative analyses [13,14]. Huang et al (2014) combined bibliometrics (quantitative technology analysis) and road-mapping (qualitative technology analysis) to examine research and development (R&D) planning.…”

“…Huang et al (2014) combined bibliometrics (quantitative technology analysis) and road-mapping (qualitative technology analysis) to examine research and development (R&D) planning. Zhang et al (2014) also conducted a technology analysis combining multivariate analysis (clustering, factor analysis, and topic model) as a quantitative approach with purposive analysis TRIZ (theory of solving inventive problem) and technology road-mapping) as a qualitative approach. Using the extracted keywords from the patent title and abstract, they carried out term clumping for technological intelligence.…”