<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rafiuddin-sen-2026-c3t">
    <titleInfo>
        <title>C³T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rifat</namePart>
        <namePart type="family">Rafiuddin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Atriya</namePart>
        <namePart type="family">Sen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study why sentiment changes in rumor-centric conversation trees by treating discourse moves such as denial/correction, evidence/link provision, and toxicity/attack as candidate interventions and asking: (i) what sentiment a reply expresses, (ii) whether the sentiment shifts relative to its parent, and (iii) which prior message most plausibly drove the reply’s sentiment. To support this setting, we introduce CASIRE, a causal sentiment reasoning layer over public rumor conversation datasets that adds post-level sentiment labels, induced parent-child shift labels, calibrated multi-label intervention tags, and explicitly annotated causal-source labels. We then propose C³T, Counterfactual Causal Conversation Transformer, a thread-structured temporal model that jointly predicts node sentiment and shifts, learns sparse ancestor attribution, and supports counterfactual queries by forcing conversational intervention embeddings on or off to estimate potential outcomes. Under an event-level split, C³T improves out-of-event robustness and attribution over text-only, graph-based, and temporal baselines, and yields interpretable model-based effects: denials/corrections and evidence reduce downstream negativity, while toxicity increases it. We also benchmark open-weight LLM prompting baselines and find that added conversational context helps, but attribution remains less reliable, motivating structure-aware counterfactual modeling for social-media analysis.</abstract>
    <identifier type="citekey">rafiuddin-sen-2026-c3t</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1357/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>30926</start>
            <end>30947</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T C³T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees
%A Rafiuddin, Rifat
%A Sen, Atriya
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F rafiuddin-sen-2026-c3t
%X Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study why sentiment changes in rumor-centric conversation trees by treating discourse moves such as denial/correction, evidence/link provision, and toxicity/attack as candidate interventions and asking: (i) what sentiment a reply expresses, (ii) whether the sentiment shifts relative to its parent, and (iii) which prior message most plausibly drove the reply’s sentiment. To support this setting, we introduce CASIRE, a causal sentiment reasoning layer over public rumor conversation datasets that adds post-level sentiment labels, induced parent-child shift labels, calibrated multi-label intervention tags, and explicitly annotated causal-source labels. We then propose C³T, Counterfactual Causal Conversation Transformer, a thread-structured temporal model that jointly predicts node sentiment and shifts, learns sparse ancestor attribution, and supports counterfactual queries by forcing conversational intervention embeddings on or off to estimate potential outcomes. Under an event-level split, C³T improves out-of-event robustness and attribution over text-only, graph-based, and temporal baselines, and yields interpretable model-based effects: denials/corrections and evidence reduce downstream negativity, while toxicity increases it. We also benchmark open-weight LLM prompting baselines and find that added conversational context helps, but attribution remains less reliable, motivating structure-aware counterfactual modeling for social-media analysis.
%U https://aclanthology.org/2026.emnlp-main.1357/
%P 30926-30947

Markdown (Informal)

[C³T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees](https://aclanthology.org/2026.emnlp-main.1357/) (Rafiuddin & Sen, EMNLP 2026)

• C³T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees (Rafiuddin & Sen, EMNLP 2026)

ACL

• Rifat Rafiuddin and Atriya Sen. 2026. C³T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 30926–30947, Budapest, Hungary. Association for Computational Linguistics.