Topic Diffusion Discovery Based on Sparseness-Constrained Non-Negative Matrix Factorization

Due to recent explosion of text data, researchers have been overwhelmed by ever-increasing volume of articles produced by different research communities. Various scholarly search websites, citation recommendation engines, and research databases have been created to simplify the text search tasks. However, it is still difficult for researchers to be able to identify potential research topics without doing intensive reviews on a tremendous number of articles published by journals, conferences, meetings, and workshops. In this paper, we consider a novel topic diffusion discovery technique that incorporates sparseness-constrained Non-negative Matrix Factorization with generalized Jensen-Shannon divergence to help understand term-topic evolutions and identify topic diffusions. Our experimental result shows that this approach can extract more prominent topics from large article databases, visualize relationships between terms of interest and abstract topics, and further help researchers understand whether given terms/topics have been widely explored or whether new topics are emerging from literature.

1. Introduction

Information and Communication Technology (ICT) have been reshaping nearly every corner of the world, especially the way of people's communication. Today, our knowledge can be easily collected, stored, and distributed digitally. Researchers have been using new communication tools to facilitate the exchange of information. However, these document (text) data have grown exponentially in recent decades, and numerous research articles are created, digitized, and stored in various research databases. It is almost impossible for a researcher to do thoroughly literature search and review on a tremendous number of articles in order to understand recent progress of his/her research of interest. Many research databases, scholarly search engines, and citation recommendation systems have been created to help tackle this problem. To gather literature related to a research is much easier today, but we are still facing challenges to determine whether a research topic (or just a term) is rarely explored by others, just emerging from discussions of small groups, or potentially connected to topics in other fields of studies-problems of topic diffusion discovery.