Tag Archives: term clustering

Does deep learning help topic extraction? A kernel k-means clustering method with word embedding

Topic extraction presents challenges for the bibliometric community, and its performance still depends on human intervention and its practical areas. This paper proposes a novel kernel k-means clustering method incorporated with a word embedding model to create a solution that effectively extracts topics from bibliometric data. The experimental results of a comparison of this method with four clustering baselines (i.e., k-means, fuzzy c-mean as,principal component analysis, and topic models) on two bibliometric datasets demonstrate its effectiveness across either a relatively broad range of disciplines or a given domain. An empirical study on bibliometric topic extraction from articles published by three top-tier bibliometric journals between 2000 and 2017, supported by expert knowledge-based evaluations, provides supplemental evidence of the method’s ability on topic extraction. Additionally, this empirical analysis reveals insights into both overlapping and diverse research interests among the three journals that would benefit journal publishers, editorial boards, and research communities.

https://doi.org/10.1016/j.joi.2018.09.004

Author(s): Yi Zhang, Jie Lu, Feng Liu, Qian Liu, Alan Porter, Hongshu Chen, Guangquan Zhang
Organization(s): University of Technology Sydney, Beijing Institute of Technology, Georgia Institute of Technology
Source: Journal of Informetrics
Year: 2018

Comparing methods to extract technical content for technological intelligence

We are developing indicators for the emergence of science and technology (S&T) topics. To do so, we extract information from various S&T information resources. This paper compares alternative ways of consolidating messy sets of key terms [e.g., using Natural Language Processing on abstracts and titles, together with various keyword sets]. Our process includes combinations of stopword removal, fuzzy term matching, association rules, and term commonality weighting. We compare topic modeling to Principal Components Analysis for a test set of 4104 abstract records on Dye-Sensitized Solar Cells. Results suggest potential to enhance understanding regarding technological topics to help track technological emergence.

Author(s): Nils C. Newman, Alan L. Porter, David Newman, Cherie Courseault Trumbach and Stephanie D. Bolan
Organization(s): Georgia Institute of Technology, University of California, University of New Orleans
Source: Journal of Engineering and Technology Management
Year: 2014
http://www.sciencedirect.com/science/article/pii/S0923474813000556