N-grams Analysis of Digital Humanities Research During 2017-2021: A Study Based on Scopus Database
| Main Authors: | Mazumder, Sourav, Barui, Tapan |
|---|---|
| Other Authors: | Babbar, Parveen, Jain, P K, Kar, Debal, Dinesh, Kumar |
| Format: | BookSection PeerReviewed Book |
| Bahasa: | eng |
| Terbitan: |
Bookwell
, 2022
|
| Subjects: | |
| Online Access: |
http://eprints.rclis.org/43231/1/ILIPS2022.pdf http://eprints.rclis.org/43231/ |
Daftar Isi:
- In the social sciences, Digital Humanities (DH) is gaining traction. An N-gram is a contiguous sequence of n words or tokens in a text document in computational linguistics and probability. In this study, authors have applied n-grams analysis to understand the context of the DH research from the abstract of 1348 articles (2017-2021). The data was collected from the Scopus database. The authors used Orage for n-grams extraction and visualised the n-grams using the word cloud. The study identified top-10 unigrams, bigrams, and trigrams and constructed the research contexts with human judgement using the frequencies of the n-grams. From the analysis authors observed some major research contexts like DH research, the use of digital technologies, ICT, social networks, cultural heritage, DH projects, and natural language processing. Bigrams were identified as more significant. This study can be helpful for scholars to understand the current research context and usage of terms.