Quantifying Individual Research's Distance from the Trends based on Dynamic Topic Modeling

Jie Meng; Wen Lou; Jiangen He

doi:10.1002/pra2.718

Quantifying Individual Research's Distance from the Trends based on Dynamic Topic Modeling

Jie Meng, Wen Lou, Jiangen He

School of Economics and Management

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Research trends are the keys for researchers to decide their research agenda. However, only few works have tried to quantify how scholars follow the trends. This paper addresses this problem by proposing a novel measurement for quantifying how a scientific entity (paper or researcher) follows the hot topics in a research field. Specifically, the topic evolution and papers are vectorizing by dynamic topic modeling. Then the degree of hotness tracing is explored from three different perspectives: mainstream, short-term direction, long-term direction. Papers and researchers in the field of Computer Vision from 2006 to 2017 were selected to evaluate our method. Further study will show the results of topic evolution patterns and researchers' clusters.

Original language	English
Pages (from-to)	762-763
Number of pages	2
Journal	Proceedings of the Association for Information Science and Technology
Volume	59
Issue number	1
DOIs	https://doi.org/10.1002/pra2.718
State	Published - 2022

Keywords

Dynamic topic modeling
Hot topics
NLP
Research behavior
Research trends

Access to Document

10.1002/pra2.718

Cite this

@article{ee5bfb45e7cd4e0bbec1d6231974e0f4,

title = "Quantifying Individual Research's Distance from the Trends based on Dynamic Topic Modeling",

abstract = "Research trends are the keys for researchers to decide their research agenda. However, only few works have tried to quantify how scholars follow the trends. This paper addresses this problem by proposing a novel measurement for quantifying how a scientific entity (paper or researcher) follows the hot topics in a research field. Specifically, the topic evolution and papers are vectorizing by dynamic topic modeling. Then the degree of hotness tracing is explored from three different perspectives: mainstream, short-term direction, long-term direction. Papers and researchers in the field of Computer Vision from 2006 to 2017 were selected to evaluate our method. Further study will show the results of topic evolution patterns and researchers' clusters.",

keywords = "Dynamic topic modeling, Hot topics, NLP, Research behavior, Research trends",

author = "Jie Meng and Wen Lou and Jiangen He",

note = "Publisher Copyright: 85 Annual Meeting of the Association for Information Science \& Technology | Oct. 29 – Nov. 1, 2022 | Pittsburgh, PA. Author(s) retain copyright, but ASIS\&T receives an exclusive publication license.",

year = "2022",

doi = "10.1002/pra2.718",

language = "英语",

volume = "59",

pages = "762--763",

journal = "Proceedings of the Association for Information Science and Technology",

issn = "2373-9231",

publisher = "John Wiley \& Sons Inc.",

number = "1",

}

TY - JOUR

T1 - Quantifying Individual Research's Distance from the Trends based on Dynamic Topic Modeling

AU - Meng, Jie

AU - Lou, Wen

AU - He, Jiangen

N1 - Publisher Copyright: 85 Annual Meeting of the Association for Information Science & Technology | Oct. 29 – Nov. 1, 2022 | Pittsburgh, PA. Author(s) retain copyright, but ASIS&T receives an exclusive publication license.

PY - 2022

Y1 - 2022

N2 - Research trends are the keys for researchers to decide their research agenda. However, only few works have tried to quantify how scholars follow the trends. This paper addresses this problem by proposing a novel measurement for quantifying how a scientific entity (paper or researcher) follows the hot topics in a research field. Specifically, the topic evolution and papers are vectorizing by dynamic topic modeling. Then the degree of hotness tracing is explored from three different perspectives: mainstream, short-term direction, long-term direction. Papers and researchers in the field of Computer Vision from 2006 to 2017 were selected to evaluate our method. Further study will show the results of topic evolution patterns and researchers' clusters.

AB - Research trends are the keys for researchers to decide their research agenda. However, only few works have tried to quantify how scholars follow the trends. This paper addresses this problem by proposing a novel measurement for quantifying how a scientific entity (paper or researcher) follows the hot topics in a research field. Specifically, the topic evolution and papers are vectorizing by dynamic topic modeling. Then the degree of hotness tracing is explored from three different perspectives: mainstream, short-term direction, long-term direction. Papers and researchers in the field of Computer Vision from 2006 to 2017 were selected to evaluate our method. Further study will show the results of topic evolution patterns and researchers' clusters.

KW - Dynamic topic modeling

KW - Hot topics

KW - NLP

KW - Research behavior

KW - Research trends

UR - https://www.scopus.com/pages/publications/85148443863

U2 - 10.1002/pra2.718

DO - 10.1002/pra2.718

M3 - 文章

AN - SCOPUS:85148443863

SN - 2373-9231

VL - 59

SP - 762

EP - 763

JO - Proceedings of the Association for Information Science and Technology

JF - Proceedings of the Association for Information Science and Technology

IS - 1

ER -

Quantifying Individual Research's Distance from the Trends based on Dynamic Topic Modeling

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this