<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2026-linguistic">
    <titleInfo>
        <title>Linguistic Cues in Political Debates: Lexical Choices and Evaluative Framing in GPT-Generated Commentary</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yu-Yu</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chung-Chi</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ming-Hung</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-444-6</identifier>
    </relatedItem>
    <abstract>Political debates shape public opinion, but many readers increasingly encounter debate takeaways through AI-generated summaries and commentary rather than full broadcasts. This paper studies whether fine-grained lexical choices in debate transcripts can influence the evaluative framing of GPT-generated political commentary. We introduce controlled word-level interventions by replacing embedding-identified key lexical items with near-synonymous alternatives, allowing us to examine how minimally invasive lexical changes affect model-generated interpretation. Across U.S. presidential debate segments, we find that single-word substitutions can shift the stance of GPT-generated commentary, but these effects are probabilistic, context-dependent, and sensitive to the speaker’s communicative goal. Substitutions are more likely to produce favorable stance shifts in critical contexts than in promotional ones, suggesting that GPT-generated commentary may amplify adversarial framing more readily than self-promotional framing. We further analyze which linguistic cue types are associated with substitution success, including sentiment direction, part of speech, and contextual suitability, and show that sentiment alone is insufficient to explain model responses. Finally, a small exploratory human evaluation suggests partial alignment between model-based stance shifts and reader preferences in promotional cases, while also revealing substantial subjectivity in human judgments. These findings highlight how candidates’ word choices may be transformed when political discourse is filtered through GPT-generated commentary, and caution against treating model-internal stance metrics as direct substitutes for large-scale human audience evaluation.</abstract>
    <identifier type="citekey">chang-etal-2026-linguistic</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-aacl.42/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>791</start>
            <end>802</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Linguistic Cues in Political Debates: Lexical Choices and Evaluative Framing in GPT-Generated Commentary
%A Chang, Yu-Yu
%A Chen, Chung-Chi
%A Wang, Ming-Hung
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F chang-etal-2026-linguistic
%X Political debates shape public opinion, but many readers increasingly encounter debate takeaways through AI-generated summaries and commentary rather than full broadcasts. This paper studies whether fine-grained lexical choices in debate transcripts can influence the evaluative framing of GPT-generated political commentary. We introduce controlled word-level interventions by replacing embedding-identified key lexical items with near-synonymous alternatives, allowing us to examine how minimally invasive lexical changes affect model-generated interpretation. Across U.S. presidential debate segments, we find that single-word substitutions can shift the stance of GPT-generated commentary, but these effects are probabilistic, context-dependent, and sensitive to the speaker’s communicative goal. Substitutions are more likely to produce favorable stance shifts in critical contexts than in promotional ones, suggesting that GPT-generated commentary may amplify adversarial framing more readily than self-promotional framing. We further analyze which linguistic cue types are associated with substitution success, including sentiment direction, part of speech, and contextual suitability, and show that sentiment alone is insufficient to explain model responses. Finally, a small exploratory human evaluation suggests partial alignment between model-based stance shifts and reader preferences in promotional cases, while also revealing substantial subjectivity in human judgments. These findings highlight how candidates’ word choices may be transformed when political discourse is filtered through GPT-generated commentary, and caution against treating model-internal stance metrics as direct substitutes for large-scale human audience evaluation.
%U https://aclanthology.org/2026.findings-aacl.42/
%P 791-802

Markdown (Informal)

[Linguistic Cues in Political Debates: Lexical Choices and Evaluative Framing in GPT-Generated Commentary](https://aclanthology.org/2026.findings-aacl.42/) (Chang et al., Findings 2026)

• Linguistic Cues in Political Debates: Lexical Choices and Evaluative Framing in GPT-Generated Commentary (Chang et al., Findings 2026)

ACL

• Yu-Yu Chang, Chung-Chi Chen, and Ming-Hung Wang. 2026. Linguistic Cues in Political Debates: Lexical Choices and Evaluative Framing in GPT-Generated Commentary. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 791–802, Hengqin, China. Association for Computational Linguistics.