Programming and Computer Software, volume 45, issue 5, pages 228-240

Stance Detection Based on Ensembles of Classifiers

Publication typeJournal Article
Publication date2019-09-01
Quartile SCImago
Q4
Quartile WOS
Q4
Impact factor0.7
ISSN03617688, 16083261
Software
Abstract
A method of stance detection in text is proposed. This method is based on the machine learning of ensembles of classifiers. It is known that ensembles have advantages over individual classifiers, which often improves the quality of classification. An important issue is determining the classifiers that should be included in such an ensemble. The method of constructing ensembles proposed in this paper, which is based on a cross-validation procedure, makes it possible to optimize the parameters of the base classifiers, evaluate the effectiveness of each combination of classifiers included in the set, and select the optimal combination. For testing the proposed method, corpora of Russian language messages in Internet forums and the social network VKontakte have been formed. These messages concern three socially significant issues—vaccination of children, Unified State Exam, and human cloning. The experimental study shows the advantage of the proposed method over other classifiers.

Citations by journals

1
2
IEEE Access
IEEE Access, 2, 28.57%
IEEE Access
2 publications, 28.57%
Neural Computing and Applications
Neural Computing and Applications, 1, 14.29%
Neural Computing and Applications
1 publication, 14.29%
Computer Speech and Language
Computer Speech and Language, 1, 14.29%
Computer Speech and Language
1 publication, 14.29%
Expert Systems with Applications
Expert Systems with Applications, 1, 14.29%
Expert Systems with Applications
1 publication, 14.29%
Web Semantics
Web Semantics, 1, 14.29%
Web Semantics
1 publication, 14.29%
Program systems theory and applications
Program systems theory and applications, 1, 14.29%
Program systems theory and applications
1 publication, 14.29%
1
2

Citations by publishers

1
2
3
Elsevier
Elsevier, 3, 42.86%
Elsevier
3 publications, 42.86%
IEEE
IEEE, 2, 28.57%
IEEE
2 publications, 28.57%
Springer Nature
Springer Nature, 1, 14.29%
Springer Nature
1 publication, 14.29%
Ailamazyan Program Systems Institute of Russian Academy of Sciences (PSI RAS)
Ailamazyan Program Systems Institute of Russian Academy of Sciences (PSI RAS), 1, 14.29%
Ailamazyan Program Systems Institute of Russian Academy of Sciences (PSI RAS)
1 publication, 14.29%
1
2
3
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Vychegzhanin S. V., Kotelnikov E. V. Stance Detection Based on Ensembles of Classifiers // Programming and Computer Software. 2019. Vol. 45. No. 5. pp. 228-240.
GOST all authors (up to 50) Copy
Vychegzhanin S. V., Kotelnikov E. V. Stance Detection Based on Ensembles of Classifiers // Programming and Computer Software. 2019. Vol. 45. No. 5. pp. 228-240.
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.1134/S0361768819050074
UR - https://doi.org/10.1134%2FS0361768819050074
TI - Stance Detection Based on Ensembles of Classifiers
T2 - Programming and Computer Software
AU - Vychegzhanin, S V
AU - Kotelnikov, E V
PY - 2019
DA - 2019/09/01 00:00:00
PB - Pleiades Publishing
SP - 228-240
IS - 5
VL - 45
SN - 0361-7688
SN - 1608-3261
ER -
BibTex |
Cite this
BibTex Copy
@article{2019_Vychegzhanin,
author = {S V Vychegzhanin and E V Kotelnikov},
title = {Stance Detection Based on Ensembles of Classifiers},
journal = {Programming and Computer Software},
year = {2019},
volume = {45},
publisher = {Pleiades Publishing},
month = {sep},
url = {https://doi.org/10.1134%2FS0361768819050074},
number = {5},
pages = {228--240},
doi = {10.1134/S0361768819050074}
}
MLA
Cite this
MLA Copy
Vychegzhanin, S. V., and E V Kotelnikov. “Stance Detection Based on Ensembles of Classifiers.” Programming and Computer Software, vol. 45, no. 5, Sep. 2019, pp. 228-240. https://doi.org/10.1134%2FS0361768819050074.
Found error?