Abstract
The topic modeling approach can indicate hidden relationships between articles in a particular academic discipline. This study aims to examine topics in library and information science (LIS) using the latent Dirichlet allocation method. From representative five journals, 1,648 full-text articles were analyzed. We labeled 30 identified topics based on the top 10 highly weighted terms for each topic, title, and body of articles. From the topic mapping, commonly used methods and shift of research issues in LIS were found.
| Original language | English |
|---|---|
| Pages (from-to) | 847-848 |
| Number of pages | 2 |
| Journal | Proceedings of the Association for Information Science and Technology |
| Volume | 55 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 2018 Jan 1 |
Fingerprint
Keywords
- latent Dirichlet allocation
- library and information science research
- mapping
- Topic modeling
ASJC Scopus subject areas
- Computer Science(all)
- Library and Information Sciences
Cite this
Analyzing library and information science full-text articles using a topic modeling approach. / Kurata, Keiko; Miyata, Yosuke; Ishita, Emi; Yamamoto, Michimasa; Yang, Fang; Iwase, Azusa.
In: Proceedings of the Association for Information Science and Technology, Vol. 55, No. 1, 01.01.2018, p. 847-848.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Analyzing library and information science full-text articles using a topic modeling approach
AU - Kurata, Keiko
AU - Miyata, Yosuke
AU - Ishita, Emi
AU - Yamamoto, Michimasa
AU - Yang, Fang
AU - Iwase, Azusa
PY - 2018/1/1
Y1 - 2018/1/1
N2 - The topic modeling approach can indicate hidden relationships between articles in a particular academic discipline. This study aims to examine topics in library and information science (LIS) using the latent Dirichlet allocation method. From representative five journals, 1,648 full-text articles were analyzed. We labeled 30 identified topics based on the top 10 highly weighted terms for each topic, title, and body of articles. From the topic mapping, commonly used methods and shift of research issues in LIS were found.
AB - The topic modeling approach can indicate hidden relationships between articles in a particular academic discipline. This study aims to examine topics in library and information science (LIS) using the latent Dirichlet allocation method. From representative five journals, 1,648 full-text articles were analyzed. We labeled 30 identified topics based on the top 10 highly weighted terms for each topic, title, and body of articles. From the topic mapping, commonly used methods and shift of research issues in LIS were found.
KW - latent Dirichlet allocation
KW - library and information science research
KW - mapping
KW - Topic modeling
UR - http://www.scopus.com/inward/record.url?scp=85064510945&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064510945&partnerID=8YFLogxK
U2 - 10.1002/pra2.2018.14505501143
DO - 10.1002/pra2.2018.14505501143
M3 - Article
AN - SCOPUS:85064510945
VL - 55
SP - 847
EP - 848
JO - Proceedings of the Association for Information Science and Technology
JF - Proceedings of the Association for Information Science and Technology
SN - 2373-9231
IS - 1
ER -