2021
DOI: 10.1108/lht-01-2021-0051
|View full text |Cite
|
Sign up to set email alerts
|

A dependency-based machine learning approach to the identification of research topics: a case in COVID-19 studies

Abstract: PurposePrevious research concerning automatic extraction of research topics mostly used rule-based or topic modeling methods, which were challenged due to the limited rules, the interpretability issue and the heavy dependence on human judgment. This study aims to address these issues with the proposal of a new method that integrates machine learning models with linguistic features for the identification of research topics.Design/methodology/approachFirst, dependency relations were used to extract noun phrases … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
11
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8

Relationship

1
7

Authors

Journals

citations
Cited by 17 publications
(11 citation statements)
references
References 41 publications
0
11
0
Order By: Relevance
“…Therefore, future research may consider employing automatic algorithms to extract topics. For example, a dependency-based machine learning approach can be used to identify research topics ( Zhu and Lei, 2021 ).…”
Section: Discussionmentioning
confidence: 99%
“…Therefore, future research may consider employing automatic algorithms to extract topics. For example, a dependency-based machine learning approach can be used to identify research topics ( Zhu and Lei, 2021 ).…”
Section: Discussionmentioning
confidence: 99%
“…Since the present study focuses motivation research in the field of SLA, research articles published in high-quality journals in this field were included. Only published research articles were included for the reason that the quality and reliability of the unpublished preprints cannot be guaranteed due to a lack of a strict quality control mechanism such as peer review ( Zhu and Lei, 2022 ). As for the selection of the high-quality journals, many research used the list of 15 journals provided by VanPatten and Williams (2002) to investigate issues in SLA.…”
Section: Methodsmentioning
confidence: 99%
“…Last, trend analyses were performed to examine the time series data, namely, the MDD values at the sentential level and that of different dependency types from 1790 to 2017. Since the MDD values were not normally distributed (e.g., p = 0.000 for MDDs in sentences with 5-10 words), we followed Zhu and Lei (2022) and employed the Mann-Kendall trend test, a commonly used nonparametric test, to detect significant trends in time series, and Theil-Sen's slope estimator to calculate the corresponding rate of change. Both tests were implemented with the Python package pyMannKendall (Hussain and Mahmud, 2019; https://github.…”
Section: Methodsmentioning
confidence: 99%