Understanding to intervene: The codesign of text classifiers with peace practitioners
Originating from a unique partnership between data scientists (datavaluepeople) and peacebuilders (Build Up), this commentary explores an innovative methodology to overcome key challenges in social media analysis by developing customized text classifiers through a participatory design approach, enga...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2024-01-01
|
| Series: | Data & Policy |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2632324924000440/type/journal_article |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846151549808541696 |
|---|---|
| author | Julie Hawke Helena Puig Larrauri Andrew Sutjahjo Benjamin Cerigo |
| author_facet | Julie Hawke Helena Puig Larrauri Andrew Sutjahjo Benjamin Cerigo |
| author_sort | Julie Hawke |
| collection | DOAJ |
| description | Originating from a unique partnership between data scientists (datavaluepeople) and peacebuilders (Build Up), this commentary explores an innovative methodology to overcome key challenges in social media analysis by developing customized text classifiers through a participatory design approach, engaging both peace practitioners and data scientists. It advocates for researchers to focus on developing frameworks that prioritize being usable and participatory in field settings, rather than perfect in simulation. Focusing on a case study investigating the polarization within online Christian communities in the United States, we outline a testing process with a dataset consisting of 8954 tweets and 10,034 Facebook posts to experiment with active learning methodologies aimed at enhancing the efficiency and accuracy of text classification. This commentary demonstrates that the inclusion of domain expertise from peace practitioners significantly refines the design and performance of text classifiers, enabling a deeper comprehension of digital conflicts. This collaborative framework seeks to transition from a data-rich, analysis-poor scenario to one where data-driven insights robustly inform peacebuilding interventions. |
| format | Article |
| id | doaj-art-80d4bd1fbd3f4f2db9f633a29994f7b6 |
| institution | Kabale University |
| issn | 2632-3249 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Data & Policy |
| spelling | doaj-art-80d4bd1fbd3f4f2db9f633a29994f7b62024-11-27T09:52:55ZengCambridge University PressData & Policy2632-32492024-01-01610.1017/dap.2024.44Understanding to intervene: The codesign of text classifiers with peace practitionersJulie Hawke0https://orcid.org/0009-0007-1898-2849Helena Puig Larrauri1Andrew Sutjahjo2Benjamin Cerigo3University of Notre Dame; Build Up, South Bend, USABuild Up, London, UKdatavaluepeople, Amsterdam, Netherlandsdatavaluepeople, Amsterdam, NetherlandsOriginating from a unique partnership between data scientists (datavaluepeople) and peacebuilders (Build Up), this commentary explores an innovative methodology to overcome key challenges in social media analysis by developing customized text classifiers through a participatory design approach, engaging both peace practitioners and data scientists. It advocates for researchers to focus on developing frameworks that prioritize being usable and participatory in field settings, rather than perfect in simulation. Focusing on a case study investigating the polarization within online Christian communities in the United States, we outline a testing process with a dataset consisting of 8954 tweets and 10,034 Facebook posts to experiment with active learning methodologies aimed at enhancing the efficiency and accuracy of text classification. This commentary demonstrates that the inclusion of domain expertise from peace practitioners significantly refines the design and performance of text classifiers, enabling a deeper comprehension of digital conflicts. This collaborative framework seeks to transition from a data-rich, analysis-poor scenario to one where data-driven insights robustly inform peacebuilding interventions.https://www.cambridge.org/core/product/identifier/S2632324924000440/type/journal_articledata sciencelarge language modelsmachine learningpeacebuildingsocial media |
| spellingShingle | Julie Hawke Helena Puig Larrauri Andrew Sutjahjo Benjamin Cerigo Understanding to intervene: The codesign of text classifiers with peace practitioners Data & Policy data science large language models machine learning peacebuilding social media |
| title | Understanding to intervene: The codesign of text classifiers with peace practitioners |
| title_full | Understanding to intervene: The codesign of text classifiers with peace practitioners |
| title_fullStr | Understanding to intervene: The codesign of text classifiers with peace practitioners |
| title_full_unstemmed | Understanding to intervene: The codesign of text classifiers with peace practitioners |
| title_short | Understanding to intervene: The codesign of text classifiers with peace practitioners |
| title_sort | understanding to intervene the codesign of text classifiers with peace practitioners |
| topic | data science large language models machine learning peacebuilding social media |
| url | https://www.cambridge.org/core/product/identifier/S2632324924000440/type/journal_article |
| work_keys_str_mv | AT juliehawke understandingtointervenethecodesignoftextclassifierswithpeacepractitioners AT helenapuiglarrauri understandingtointervenethecodesignoftextclassifierswithpeacepractitioners AT andrewsutjahjo understandingtointervenethecodesignoftextclassifierswithpeacepractitioners AT benjamincerigo understandingtointervenethecodesignoftextclassifierswithpeacepractitioners |