“Term clumping” for technical intelligence: A case study on dye-sensitized solar cells
Technological Forecasting and Social ChangePublished 28 January 2014
Yi Zhang, Alan L. Porter, Zhengyin Hu, Ying Guo, Nils C. Newman
Citations157
SJR quartileQ1
SJR score3.47
SNIP3.25
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Six "term clumping" steps that can clean and consolidate topical content in text sources and are better suited to contributing usable technical intelligence than the original results are presented.
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.
Keywords
Computer ScienceDecision SciencesMaterials Science
NatureA low-cost, high-efficiency solar cell based on dye-sensitized colloidal TiO2 films
28,400 Citations1991Brian C. O’Regan, Michaël Grätzel
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
Journal of the American Society for Information ScienceIndexing by latent semantic analysis
12,677 Citations1990Scott Deerwester, Susan Dumais +3 more
A Survey of Dimension Reduction Techniques
1,123 Citations2002Imola K. Fodor
Several dimension reduction methods are described that can be applied to high-dimensional datasets to reduce the dimension of the original data prior to any modeling ofmore » the data.
Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)Topic Detection and Tracking Pilot Study Final Report
951 Citations2018James Allan, Jaime Carbonell +3 more
Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
662 Citations2006
This volume serves as the written record of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-06) held in Philadelphia, Pennsylvania on August 20- 23, 2006.
Tech Mining: Exploiting New Technologies for Competitive Advantage
418 Citations2004Alan L. Porter, Scott W. Cunningham
Survey of Text Mining: Clustering, Classification, and Retrieval
408 Citations2007Michael W. Berry, Malú Castellanos
Survey of Text Mining II offers a broad selection in state-of-the art algorithms and software for text mining from both academic and industrial perspectives, to generate interest and insight into the state of the field.
Technological Forecasting and Social ChangeTechnology opportunities analysis
279 Citations1995Alan L. Porter, Michael J. Detampel
The range of information profiles possible by examining research and development publications and patents pertaining to electronics assembly and, more specifically, to multichip module development is illustrated.
Technological Forecasting and Social ChangeAutomated extraction and visualization of information for technological intelligence and forecasting
194 Citations2002Donghua Zhu, Alan L. Porter
Empirical technology forecasting is not well utilized in technology management and efforts to address these three factors via partially automated processes to generate helpful knowledge from text quickly and graphically are reported on.
PLoS ONESystemic Stimulation of TLR2 Impairs Neonatal Mouse Brain Development
177 Citations2011Xiaonan Du, Bobbi Fleiss +8 more
Repeated systemic exposure to the TLR2 agonist Pam3CSK4 can have a short-term negative impact on the neonatal mouse brain, although long-term memory function and the volume of gray or white matter are not affected.
Journal of Intelligent Information SystemsTextual Data Mining to Support Science and Technology Management
169 Citations2000Paul Losiewicz, Douglas W. Oard +1 more
A textual data mining architecture that extends a classic paradigm for knowledge discovery in databases is introduced, and a broad view of data mining—the process of discovering patterns in large collections of data—is described in some detail.
Technological Forecasting and Social ChangeForecasting Innovation Pathways (FIP) for new and emerging science and technologies
154 Citations2011Douglas K. R. Robinson, Lu Huang +2 more
A framework to analyze NESTs to help ascertain likely innovation pathways and a 10-step framework based on extensive Future-oriented Technology Analyses ("FTA") experience, enriched by in-depth case analyses is devised.
A mixture model for contextual text mining
122 Citations2006Qiaozhu Mei, ChengXiang Zhai
A new general probabilistic model for contextual text mining is proposed that can cover several existing models as special cases and can be applied to many interesting mining tasks, such as temporal text mining, spatiotemporal textmining, author-topic analysis, and cross-collection comparative analysis.
Using latent semantic analysis to identify similarities in source code to support program understanding
100 Citations2002Jonathan I. Maletic, Andrian Marcus
The paper describes the results of applying Latent Semantic Analysis (LSA), an advanced information retrieval method, to program source code and associated documentation to assist in the understanding of a nontrivial software system, namely a version of Mosaic.
Research EvaluationAdvanced bibliometric methods to assess research performance and scientific development: basic principles and recent practical applications
97 Citations1993Anthony F. J. van Raan
A broad overview is presented of quantitative methods, based on bibliometric data, for constructingSpecific indicators for important aspects of scientific research can be constructed, the main types being characteristics of scientific output; characteristics of science impact; and maps of science.
Patent claim processing for readability
83 Citations2003Akihiro Shinmori, Manabu Okumura +2 more
This work is currently investigating a method to clarify terms in patent claims and to find the explanatory portions from the detailed description part of the patent specifications through both approaches, and believes it can improve readability of patent claims.
Technology Analysis and Strategic ManagementA hybrid visualisation model for technology roadmapping: bibliometrics, qualitative methodology and empirical study
76 Citations2013Yi Zhang, Ying Guo +3 more
This paper integrates bibliometrics with qualitative methodologies and visualisation techniques to construct a hybrid model for composing technology roadmaps and generates a global technology roadmap for electric vehicles to demonstrate the approach in an empirical study.
Latent semantic space
62 Citations2000Rie Kubota Ando
A novel algorithm that creates document vectors with reduced dimensionality by iteratively "scaling" vectors and computing eigenvectors is presented, which breaks the symmetry of documents and terms to capture information more evenly across documents.
ScientometricsTriple Helix innovation in China’s dye-sensitized solar cell industry: hybrid methods with semantic TRIZ and technology roadmapping
61 Citations2013Yi Zhang, Xiao Zhou +3 more
This paper explores how bibliometrics and text mining can inform Triple Helix analyses and engages Competitive Technical Intelligence concepts and methods for studies of Newly Emerging Science & Technology in support of technology management and policy.
Journal of the American Society for Information ScienceClumping properties of content‐bearing words
49 Citations1998Abraham Bookstein, Shmuel T. Klein +1 more
The notion of serial clustering of words in text is defined, and the value of such clustering as an indicator of a word's bearing content is explored.
Automatic discovery of technology trends from patent text
48 Citations2009Youngho Kim, Yingshi Tian +3 more
This paper combines a probabilistic approach by adopting linguistic clues and an unsupervised procedure to discover technological trends and is promising not only in its accuracy, 77% in R-precision, but also in its functionality and novelty of discovering meaningful technological trends.
Technology Analysis and Strategic ManagementText mining of information resources to inform Forecasting Innovation Pathways
46 Citations2012Ying Guo, Tingting Ma +2 more
This paper explores the systematisation of the ‘Forecasting Innovation Pathways’ analytical approach through the application of Tech Mining, and devise a means to help extract intelligence on key technology components and functions, major stakeholders, and potential applications.
Journal of Engineering and Technology ManagementComparing methods to extract technical content for technological intelligence
45 Citations2013Nils C. Newman, Alan L. Porter +3 more
This presentation compares alternative ways of consolidating messy sets of key terms and compares PCA results to topic modeling results, suggesting good potential to enhance technical intelligence payoffs from database searches on topics of interest.
Detecting emerging concepts in textual data mining
42 Citations2001William M. Pottenger, Ting‐Hao Yang
This article summarizes the research to date in the automatic identi cation of emerging trends in textual data and suggests opportunities for further research and development in this area.
PLoS ONEFunctional Cohesion of Gene Sets Determined by Latent Semantic Indexing of PubMed Abstracts
37 Citations2011Lijing Xu, Nicholas A. Furlotte +5 more
This work implemented Latent Semantic Indexing (LSI) to determine the functional coherence of gene sets and found that approximately 75% of genes in GO biological process category and 90% of the gene sets in GO molecular function and cellular component categories were functionally cohesive (LPv<0.05).
R and D ManagementEmpirically informing a technology delivery system model for an emerging technology: illustrated for dye‐sensitized solar cells
33 Citations2012Ying Guo, Xu Chen +2 more
A 10‐step analytical approach is presented to help characterize the technology, gauge its state of development, and depict the socio‐technical system institutions and actors and a new ‘cross‐charting’ method appears effective at associating novel technology‐enabled capabilities to gain functional advantages, and to link those functions to potential applications.
Semantic language models for topic detection and tracking
33 Citations2003Ramesh Nallapati
In this work, a new semantic language modeling approach to model news stories in the Topic Detection and Tracking (TDT) task is presented, which builds a unigram language model for each semantic class in a news story.
Journal of Information ScienceIdentifying synonymous concepts in preparation for technology mining
25 Citations2007Cherie Courseault Trumbach, Dinah Payne
The development of a `concept-clumping algorithm' designed to improve the clustering of technical concepts is demonstrated and it is found that the algorithm has an 89—91% precision rate, was successful in moving technically important terms higher in the term frequency list, and improved the technical specificity of term clusters.
Journal of the American Society for Information Science and TechnologyAdapting measures of clumping strength to assess term‐term similarity
14 Citations2003Abraham Bookstein, Vladimir Kulyukin +2 more
This paper examines statistical patterns expected of a pair of terms that are semantically related to each other, and derives measures of how tightly two terms areSemantically associated, to probe whether such measures yield reasonable results.
Medical Entomology and ZoologyThe Information Revolution: Current and Future Consequences
13 Citations1998Alan L. Porter, William H. Read
This book discusses implications for modern management, politics, education, and the workplace of the Information Revolution in the age of information.
Lecture notes in computer scienceTOAS intelligence mining; analysis of natural language processing and computational linguistics
11 Citations1997Robert J. Watts, Alan L. Porter +2 more
The Technology Opportunities Analysis System, a software system, extracts useful information from literature abstract files that have identified fields that repeat in each abstract record of specific databases, such as Engineering Index, INSPEC, Business Index, U.S. Patents, and the National Technical Information Service (NTIS) Research Reports.
Lecture notes in computer scienceLRLW-LSI: An Improved Latent Semantic Indexing (LSI) Text Classifier
7 Citations2008Ding Wang, Songnian Yu +3 more
Experimental results show that the proposed new local Latent Semantic Indexing method, called "Local Relevancy Ladder-Weighted LSI", is much better than global LSI and traditional local LSI methods on classification within a much smaller LSI dimension.
Journal of the American Society for Information Science and TechnologyDiscovering term occurrence structure in text
5 Citations2001Abraham Bookstein, T. Raita
Journal of the American Society for Information Science and TechnologyDiscovering term occurrence structure in text
5 Citations2001Abraham Bookstein, T. Raita
A new type of clumping measure, which extends the earlier measures by permitting gaps within a clump, is defined, and several variants examined.
Mining foreign language information resources
4 Citations2003Robert J. Watts, Alan L. Porter
This paper presents an initial foray into extracting information from non-English resources through text mining software called the "Technology Opportunities Analysis System" (TOAS), which is oriented explicitly to technology management purposes.
Comparing methods to extract technical content for technological intelligence
4 Citations2012Nils C. Newman, Alan L. Porter +3 more