Diffusion of latent semantic analysis as a research tool: A social network analysis approach

Yaşar Tonta,Hamid R Darvish

doi:10.1016/j.joi.2009.11.003

Yaşar Tonta, Hamid R Darvish

Open Access

https://doi.org/10.1016/j.joi.2009.11.003

Copy DOI

Abstract

Latent semantic analysis (LSA) is a relatively new research tool with a wide range of applications in different fields ranging from discourse analysis to cognitive science, from information retrieval to machine learning and so on. In this paper, we chart the development and diffusion of LSA as a research tool using social network analysis (SNA) approach that reveals the social structure of a discipline in terms of collaboration among scientists. Using Thomson Reuters’ Web of Science (WoS), we identified 65 papers with “latent semantic analysis” in their titles and 250 papers in their topics (but not in titles) between 1990 and 2008. We then analyzed those papers using bibliometric and SNA techniques such as co-authorship and cluster analysis. It appears that as the emphasis moves from the research tool (LSA) itself to its applications in different fields, citations to papers with LSA in their titles tend to decrease. The productivity of authors fits Lotka's Law while the network of authors is quite loose. Networks of journals cited in papers with LSA in their titles and topics are well connected.

Highlights

The technique of Latent Semantic Analysis (LSA) was patented on June 13, 1989 by Deerwester et al (1989)
CiteSpace5 was used to depict the structure of social network as well as to identify the cluster labels in the network of journals cited in papers with LSA in their titles and topics (Chen, 2006)
LSA was patented by Deerwester et al in 1989, the very first journal article by the same authors entitled “Indexing by Latent Semantic Analysis” was published in the Journal of the American Society for Information Science in 1990 (Deerwester et al, 1990)

Summary

Introduction

The technique of Latent Semantic Analysis (LSA) was patented on June 13, 1989 by Deerwester et al (1989). We attempt to chart the development and diffusion of LSA as a research tool by combining bibliometric and social network analysis techniques such as citation analysis, co-authorship analysis and cluster analysis. SNA is based on graph theory and uses terms such as density (connectedness of the graph) and centrality measures (relationships between nodes in terms of degree, closeness and betweenness) to conceptualize social structures as networks (Otte & Rousseau, 2002).

Results

Conclusion