@inproceedings{alba-etal-2025-towards,
title = "Towards Robust Sentiment Analysis of Temporally-Sensitive Policy-Related Online Text",
author = "Alba, Charles and
Warner, Benjamin C and
Saxena, Akshar and
Huang, Jiaxin and
An, Ruopeng",
editor = "Zhao, Jin and
Wang, Mingyang and
Liu, Zhu",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-srw.70/",
doi = "10.18653/v1/2025.acl-srw.70",
pages = "958--976",
ISBN = "979-8-89176-254-1",
abstract = "Sentiment analysis in policy-related studies typically involves annotating a subset of data to fine-tune a pre-trained model, which is subsequently used to classify sentiments in the remaining unlabeled texts, enabling policy researchers to analyze sentiments in novel policy contexts under resource constraints. We argue that existing methods fail to adequately capture the temporal volatility inherent in policy-related sentiments, which are subject to external shocks and evolving discourse of opinions. We propose methods accounting for the temporal dynamics of policy-related texts. Specifically, we propose leveraging continuous time-series clustering to select data points for annotation based on temporal trends and subsequently apply model merging techniques $-$ each fine-tuned separately on data from distinct time intervals. Our results indicate that continuous time-series clustering followed by fine-tuning a single unified model achieves superior performance, outperforming existing methods by an average F1-score of 2.71{\%}. This suggests that language models can generalize to temporally sensitive texts when provided with temporally representative samples. Nevertheless, merging multiple time-specific models $-$ particularly via greedy soup and TIES $-$ achieves competitive performance, suggesting practical applications in dynamically evolving policy scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alba-etal-2025-towards">
<titleInfo>
<title>Towards Robust Sentiment Analysis of Temporally-Sensitive Policy-Related Online Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Alba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Warner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshar</namePart>
<namePart type="family">Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruopeng</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-254-1</identifier>
</relatedItem>
<abstract>Sentiment analysis in policy-related studies typically involves annotating a subset of data to fine-tune a pre-trained model, which is subsequently used to classify sentiments in the remaining unlabeled texts, enabling policy researchers to analyze sentiments in novel policy contexts under resource constraints. We argue that existing methods fail to adequately capture the temporal volatility inherent in policy-related sentiments, which are subject to external shocks and evolving discourse of opinions. We propose methods accounting for the temporal dynamics of policy-related texts. Specifically, we propose leveraging continuous time-series clustering to select data points for annotation based on temporal trends and subsequently apply model merging techniques - each fine-tuned separately on data from distinct time intervals. Our results indicate that continuous time-series clustering followed by fine-tuning a single unified model achieves superior performance, outperforming existing methods by an average F1-score of 2.71%. This suggests that language models can generalize to temporally sensitive texts when provided with temporally representative samples. Nevertheless, merging multiple time-specific models - particularly via greedy soup and TIES - achieves competitive performance, suggesting practical applications in dynamically evolving policy scenarios.</abstract>
<identifier type="citekey">alba-etal-2025-towards</identifier>
<identifier type="doi">10.18653/v1/2025.acl-srw.70</identifier>
<location>
<url>https://aclanthology.org/2025.acl-srw.70/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>958</start>
<end>976</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Robust Sentiment Analysis of Temporally-Sensitive Policy-Related Online Text
%A Alba, Charles
%A Warner, Benjamin C.
%A Saxena, Akshar
%A Huang, Jiaxin
%A An, Ruopeng
%Y Zhao, Jin
%Y Wang, Mingyang
%Y Liu, Zhu
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-254-1
%F alba-etal-2025-towards
%X Sentiment analysis in policy-related studies typically involves annotating a subset of data to fine-tune a pre-trained model, which is subsequently used to classify sentiments in the remaining unlabeled texts, enabling policy researchers to analyze sentiments in novel policy contexts under resource constraints. We argue that existing methods fail to adequately capture the temporal volatility inherent in policy-related sentiments, which are subject to external shocks and evolving discourse of opinions. We propose methods accounting for the temporal dynamics of policy-related texts. Specifically, we propose leveraging continuous time-series clustering to select data points for annotation based on temporal trends and subsequently apply model merging techniques - each fine-tuned separately on data from distinct time intervals. Our results indicate that continuous time-series clustering followed by fine-tuning a single unified model achieves superior performance, outperforming existing methods by an average F1-score of 2.71%. This suggests that language models can generalize to temporally sensitive texts when provided with temporally representative samples. Nevertheless, merging multiple time-specific models - particularly via greedy soup and TIES - achieves competitive performance, suggesting practical applications in dynamically evolving policy scenarios.
%R 10.18653/v1/2025.acl-srw.70
%U https://aclanthology.org/2025.acl-srw.70/
%U https://doi.org/10.18653/v1/2025.acl-srw.70
%P 958-976
Markdown (Informal)
[Towards Robust Sentiment Analysis of Temporally-Sensitive Policy-Related Online Text](https://aclanthology.org/2025.acl-srw.70/) (Alba et al., ACL 2025)
ACL