Big data and democratic speech: Predicting deliberative quality using machine learning techniques
This article explores techniques for using supervised machine learning to study discourse quality in large datasets. We explain and illustrate the computational techniques that we have developed to facilitate a large-scale study of deliberative quality in Canada’s three northern territories: Yukon,...
Published in: | Methodological Innovations |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
SAGE Publications
2021
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1177/20597991211010416 http://journals.sagepub.com/doi/pdf/10.1177/20597991211010416 http://journals.sagepub.com/doi/full-xml/10.1177/20597991211010416 |
id |
crsagepubl:10.1177/20597991211010416 |
---|---|
record_format |
openpolar |
spelling |
crsagepubl:10.1177/20597991211010416 2023-05-15T17:46:40+02:00 Big data and democratic speech: Predicting deliberative quality using machine learning techniques Fournier-Tombs, Eleonore MacKenzie, Michael K. 2021 http://dx.doi.org/10.1177/20597991211010416 http://journals.sagepub.com/doi/pdf/10.1177/20597991211010416 http://journals.sagepub.com/doi/full-xml/10.1177/20597991211010416 en eng SAGE Publications https://creativecommons.org/licenses/by-nc/4.0/ CC-BY-NC Methodological Innovations volume 14, issue 2, page 205979912110104 ISSN 2059-7991 2059-7991 Social Sciences (miscellaneous) Sociology and Political Science journal-article 2021 crsagepubl https://doi.org/10.1177/20597991211010416 2022-09-21T19:51:04Z This article explores techniques for using supervised machine learning to study discourse quality in large datasets. We explain and illustrate the computational techniques that we have developed to facilitate a large-scale study of deliberative quality in Canada’s three northern territories: Yukon, Northwest Territories, and Nunavut. This larger study involves conducting comparative analyses of hundreds of thousands of parliamentary speech acts since the creation of Nunavut 20 years ago. Without computational techniques, we would be unable to conduct such an ambitious and comprehensive analysis of deliberative quality. The purpose of this article is to demonstrate the machine learning techniques that we have developed with the hope that they might be used and improved by other communications scholars who are interested in conducting textual analyses using large datasets. Other possible applications of these techniques might include analyses of campaign speeches, party platforms, legislation, judicial rulings, online comments, newspaper articles, and television or radio commentaries. Article in Journal/Newspaper Northwest Territories Nunavut Yukon SAGE Publications (via Crossref) Northwest Territories Nunavut Yukon Methodological Innovations 14 2 205979912110104 |
institution |
Open Polar |
collection |
SAGE Publications (via Crossref) |
op_collection_id |
crsagepubl |
language |
English |
topic |
Social Sciences (miscellaneous) Sociology and Political Science |
spellingShingle |
Social Sciences (miscellaneous) Sociology and Political Science Fournier-Tombs, Eleonore MacKenzie, Michael K. Big data and democratic speech: Predicting deliberative quality using machine learning techniques |
topic_facet |
Social Sciences (miscellaneous) Sociology and Political Science |
description |
This article explores techniques for using supervised machine learning to study discourse quality in large datasets. We explain and illustrate the computational techniques that we have developed to facilitate a large-scale study of deliberative quality in Canada’s three northern territories: Yukon, Northwest Territories, and Nunavut. This larger study involves conducting comparative analyses of hundreds of thousands of parliamentary speech acts since the creation of Nunavut 20 years ago. Without computational techniques, we would be unable to conduct such an ambitious and comprehensive analysis of deliberative quality. The purpose of this article is to demonstrate the machine learning techniques that we have developed with the hope that they might be used and improved by other communications scholars who are interested in conducting textual analyses using large datasets. Other possible applications of these techniques might include analyses of campaign speeches, party platforms, legislation, judicial rulings, online comments, newspaper articles, and television or radio commentaries. |
format |
Article in Journal/Newspaper |
author |
Fournier-Tombs, Eleonore MacKenzie, Michael K. |
author_facet |
Fournier-Tombs, Eleonore MacKenzie, Michael K. |
author_sort |
Fournier-Tombs, Eleonore |
title |
Big data and democratic speech: Predicting deliberative quality using machine learning techniques |
title_short |
Big data and democratic speech: Predicting deliberative quality using machine learning techniques |
title_full |
Big data and democratic speech: Predicting deliberative quality using machine learning techniques |
title_fullStr |
Big data and democratic speech: Predicting deliberative quality using machine learning techniques |
title_full_unstemmed |
Big data and democratic speech: Predicting deliberative quality using machine learning techniques |
title_sort |
big data and democratic speech: predicting deliberative quality using machine learning techniques |
publisher |
SAGE Publications |
publishDate |
2021 |
url |
http://dx.doi.org/10.1177/20597991211010416 http://journals.sagepub.com/doi/pdf/10.1177/20597991211010416 http://journals.sagepub.com/doi/full-xml/10.1177/20597991211010416 |
geographic |
Northwest Territories Nunavut Yukon |
geographic_facet |
Northwest Territories Nunavut Yukon |
genre |
Northwest Territories Nunavut Yukon |
genre_facet |
Northwest Territories Nunavut Yukon |
op_source |
Methodological Innovations volume 14, issue 2, page 205979912110104 ISSN 2059-7991 2059-7991 |
op_rights |
https://creativecommons.org/licenses/by-nc/4.0/ |
op_rightsnorm |
CC-BY-NC |
op_doi |
https://doi.org/10.1177/20597991211010416 |
container_title |
Methodological Innovations |
container_volume |
14 |
container_issue |
2 |
container_start_page |
205979912110104 |
_version_ |
1766150451701481472 |