Comparative Analysis of Community Detection and
Transformer-Based Approaches for Topic Clustering of Scientific
Papers

D 2023

Comparative Analysis of Community Detection and Transformer-Based Approaches for Topic Clustering of Scientific Papers

BRETSKO, Daniel, Aliaksandr BELY and Stanislav SOBOLEVSKY

Basic information

Original name

Comparative Analysis of Community Detection and Transformer-Based Approaches for Topic Clustering of Scientific Papers

Authors

BRETSKO, Daniel (804 Ukraine, guarantor, belonging to the institution), Aliaksandr BELY (112 Belarus, belonging to the institution) and Stanislav SOBOLEVSKY (112 Belarus, belonging to the institution)

Edition

Cham, 23rd International Conference on Computational Science and Its Applications , ICCSA 2023, p. 648-660, 13 pp. 2023

Publisher

Springer

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Germany

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

References:

URL

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14310/23:00131468

Organization unit

Faculty of Science

ISBN

978-3-031-36804-2

ISSN

DOI

http://dx.doi.org/10.1007/978-3-031-36805-9_42

UT WoS

001166618800042

Keywords in English

Network analysis; NLP; Topic clustering; Community detection; Sentence-transformers

Abstract

V originále

We are solving the topic clustering problem, where we need to categorize papers with initially available subjects into more consistent and higher-level topics. We approach the task from two perspectives, one is the traditional network science, where we perform community detection on a subject network with the use of Combo algorithm, and the second is the transformer-based top2vec algorithm which uses sentence-transformer to embed the content of the papers. The comparison between the two approaches was conducted using a dataset of scientific papers on computer science and mathematics collected from the SCOPUS database, and different coherence scores were used as a measure of performance. The results showed that the community detection Combo algorithm was able to achieve a similar coherence score to the transformer-based top2vec. The findings suggest that community detection may be a viable alternative for topic clustering when one has predefined topics, especially when a high coherence score and fast processing time are desired. The paper also discusses the potential advantages and limitations of using Combo for topic clustering and the potential for future work in this area.

Links

EF16_019/0000822, research and development project

Name: Centrum excelence pro kyberkriminalitu, kyberbezpečnost a ochranu kritických informačních infrastruktur

MUNI/J/0008/2021, interní kód MU

Name: Digital City

Investor: Masaryk University, MASH JUNIOR - MUNI Award In Science and Humanities JUNIOR

Citovat

BRETSKO, Daniel, Aliaksandr BELY and Stanislav SOBOLEVSKY. Comparative Analysis of Community Detection and Transformer-Based Approaches for Topic Clustering of Scientific Papers. In Osvaldo Gervasi, Beniamino Murgante, David Taniar, Bernady O. Apduhan, Ana Cristina Braga, Chiara Garau, Anastasia Stratigea. 23rd International Conference on Computational Science and Its Applications , ICCSA 2023. Cham: Springer, 2023, p. 648-660. ISBN 978-3-031-36804-2. Available from: https://dx.doi.org/10.1007/978-3-031-36805-9_42.

@inproceedings{2303537,
   author = {Bretsko, Daniel and Bely, Aliaksandr and Sobolevsky, Stanislav},
   address = {Cham},
   booktitle = {23rd International Conference on Computational Science and Its Applications , ICCSA 2023},
   doi = {http://dx.doi.org/10.1007/978-3-031-36805-9_42},
   editor = {Osvaldo Gervasi, Beniamino Murgante, David Taniar, Bernady O. Apduhan, Ana Cristina Braga, Chiara Garau, Anastasia Stratigea},
   keywords = {Network analysis; NLP; Topic clustering; Community detection; Sentence-transformers},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Cham},
   isbn = {978-3-031-36804-2},
   pages = {648-660},
   publisher = {Springer},
   title = {Comparative Analysis of Community Detection and Transformer-Based Approaches for Topic Clustering of Scientific Papers},
   url = {https://link.springer.com/chapter/10.1007/978-3-031-36805-9_42},
   year = {2023}
}

TY  - JOUR
ID  - 2303537
AU  - Bretsko, Daniel - Bely, Aliaksandr - Sobolevsky, Stanislav
PY  - 2023
TI  - Comparative Analysis of Community Detection and Transformer-Based Approaches for Topic Clustering of Scientific Papers
PB  - Springer
CY  - Cham
SN  - 9783031368042
KW  - Network analysis
KW  - NLP
KW  - Topic clustering
KW  - Community detection
KW  - Sentence-transformers
UR  - https://link.springer.com/chapter/10.1007/978-3-031-36805-9_42
N2  - We are solving the topic clustering problem, where we need to categorize papers with initially available subjects into more consistent and higher-level topics. We approach the task from two perspectives, one is the traditional network science, where we perform community detection on a subject network with the use of Combo algorithm, and the second is the transformer-based top2vec algorithm which uses sentence-transformer to embed the content of the papers. The comparison between the two approaches was conducted using a dataset of scientific papers on computer science and mathematics collected from the SCOPUS database, and different coherence scores were used as a measure of performance. The results showed that the community detection Combo algorithm was able to achieve a similar coherence score to the transformer-based top2vec. The findings suggest that community detection may be a viable alternative for topic clustering when one has predefined topics, especially when a high coherence score and fast processing time are desired. The paper also discusses the potential advantages and limitations of using Combo for topic clustering and the potential for future work in this area.
ER  -

BRETSKO, Daniel, Aliaksandr BELY and Stanislav SOBOLEVSKY. Comparative Analysis of Community Detection and Transformer-Based Approaches for Topic Clustering of Scientific Papers. In Osvaldo Gervasi, Beniamino Murgante, David Taniar, Bernady O. Apduhan, Ana Cristina Braga, Chiara Garau, Anastasia Stratigea. \textit{23rd International Conference on Computational Science and Its Applications , ICCSA 2023}. Cham: Springer, 2023, p.~648-660. ISBN~978-3-031-36804-2. Available from: https://dx.doi.org/10.1007/978-3-031-36805-9\_{}42.

Detailed Information on Publication Record