Abstract
Studying research fronts enables researchers to understand how their academic fields emerged, how they are currently developing and their changes over time. While topic modelling tools help discover themes in documents, they employ a “bag-of-words” approach and require researchers to manually label categories, specify the number of topics a priori, and make assumptions about word distributions in documents. This paper proposes an alternative approach based on entity linking, which links word strings to entities from a knowledge base, to help solve issues associated with “bag-of-words” approaches by automatically identifying topics based on entity mentions. To study topic trends and popularity, we use four indicators—Mann–Kendall’s test, Sen’s slope analysis, z-score values and Kleinberg’s burst detection algorithm. The combination of these indicators helps us understand which topics are particularly active (“hot” topics), which are decreasing (“cold” topics or past “bursty” topics) and which are maturely developed. We apply the approach and indicators to the fields of Information Science and Accounting.
Highlights
As ever more academic articles are published, it becomes increasingly challenging for researchers to orient themselves and to remain informed of developments in their rapidly diversifying academic fields
We present our method based on entity linking as a way of overcoming limitations associated with various existing methods in this category, including their employment of a “bag-of-words” approach, and their requirement for researchers to manually label categories, specify the number of topics to emerge from the data, and make assumptions about the distributions of words included in the documents (Lee and Kang 2018)
While we follow previous literature in using z-scores and the Kleinberg’s burst-detection algorithm, we introduce the use of Mann–Kendall’s test and Sen’s slope analysis to examine topic trends
Summary
As ever more academic articles are published, it becomes increasingly challenging for researchers to orient themselves and to remain informed of developments in their rapidly diversifying academic fields. Identifying “core” topics is of great interest to government, industry (Small et al 2014) and academia (Lee and Kang 2018). The detection of “core” topics is of great interest to government, industry (Small et al 2014) and. Through analysing which topics are rising or falling in popularity, governmental funding boards can make decisions regarding grant allocation to promising areas, companies can design Research and Development (R&D) pursuits for promising technologies and researchers can identify promising topics upon which to focus their work (Lee and Kang 2018). The ability to understand and synthesize historical and emerging ideas, through the analysis of topics, is crucial for researchers to gain insights into how relevant modes of analysis, methods, theory and context are developing (Nederhof and Van Wijk 1997), to generate novel concepts and methods, and for their academic fields to progress (Westgate et al 2015)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
