WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover’s Distance in Sociocultural Analysis

Mikael Brunila, Jack LaViolette


Abstract
Despite the increasing popularity of NLP in the humanities and social sciences, advances in model performance and complexity have been accompanied by concerns about interpretability and explanatory power for sociocultural analysis. One popular model that takes a middle road is Word Mover’s Distance (WMD). Ostensibly adapted for its interpretability, WMD has nonetheless been used and further developed in ways which frequently discard its most interpretable aspect: namely, the word-level distances required for translating a set of words into another set of words. To address this apparent gap, we introduce WMDecompose: a model and Python library that 1) decomposes document-level distances into their constituent word-level distances, and 2) subsequently clusters words to induce thematic elements, such that useful lexical information is retained and summarized for analysis. To illustrate its potential in a social scientific context, we apply it to a longitudinal social media corpus to explore the interrelationship between conspiracy theories and conservative American discourses. Finally, because of the full WMD model’s high time-complexity, we additionally suggest a method of sampling document pairs from large datasets in a reproducible way, with tight bounds that prevent extrapolation of unreliable results due to poor sampling practices.
Anthology ID:
2021.latechclfl-1.18
Volume:
Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic (online)
Editors:
Stefania Degaetano-Ortlieb, Anna Kazantseva, Nils Reiter, Stan Szpakowicz
Venue:
LaTeCHCLfL
SIG:
SIGHUM
Publisher:
Association for Computational Linguistics
Note:
Pages:
154–167
Language:
URL:
https://aclanthology.org/2021.latechclfl-1.18
DOI:
10.18653/v1/2021.latechclfl-1.18
Bibkey:
Cite (ACL):
Mikael Brunila and Jack LaViolette. 2021. WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover’s Distance in Sociocultural Analysis. In Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 154–167, Punta Cana, Dominican Republic (online). Association for Computational Linguistics.
Cite (Informal):
WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover’s Distance in Sociocultural Analysis (Brunila & LaViolette, LaTeCHCLfL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.latechclfl-1.18.pdf
Video:
 https://aclanthology.org/2021.latechclfl-1.18.mp4
Code
 maybemkl/wmdecompose