<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vidigal-2026-textblob">
    <titleInfo>
        <title>From TextBlob to LLM Agents: Sentiment Model Selection for B2B Technical Support with CSAT Ground Truth</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pedro</namePart>
        <namePart type="family">Vidigal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Georg</namePart>
            <namePart type="family">Rehm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mei</namePart>
            <namePart type="family">Tu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-394-4</identifier>
    </relatedItem>
    <abstract>We present a five-year case study of sentiment model selection for customer satisfaction (CSAT) prediction in B2B technical support. Our evaluation uses the complete population of CSAT-rated tickets from an enterprise software company: over 500 tickets comprising \sim2,500 customer comments from 100+ organizations over five years. We evaluate 17 approaches across 5 paradigms (lexicon, off-the-shelf transformers, NLI zero-shot, multi-task LLM agent, and 12 dedicated LLM agents from 6 vendor families), plus 11 fine-tuning experiments (all achieving MCCłeq0). Key findings: (1) a dedicated single-task LLM agent reduces neutral bias from 69% to 22%, improving MCC from -0.018 to 0.347 (p&lt;0.001); (2) our results are consistent with the “Alignment Tax” (Lin et al., 2024; Wu et al., 2025) in sentiment classification: Claude Opus 4.6 exhibits 41% neutral predictions and lower recall than its budget model Haiku 4.5 (p=0.003); (3) \sim38% of dissatisfied customers are undetectable by all 12 LLMs due to administrative requests lacking emotional language; (4) Gemini 3 Flash achieves the best MCC (0.347) at 0.60/1K, over 100× cheaper than Claude Opus. We describe the three-phase production deployment and provide practitioner recommendations.</abstract>
    <identifier type="citekey">vidigal-2026-textblob</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-industry.121/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1774</start>
            <end>1782</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T From TextBlob to LLM Agents: Sentiment Model Selection for B2B Technical Support with CSAT Ground Truth
%A Vidigal, Pedro
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F vidigal-2026-textblob
%X We present a five-year case study of sentiment model selection for customer satisfaction (CSAT) prediction in B2B technical support. Our evaluation uses the complete population of CSAT-rated tickets from an enterprise software company: over 500 tickets comprising \sim2,500 customer comments from 100+ organizations over five years. We evaluate 17 approaches across 5 paradigms (lexicon, off-the-shelf transformers, NLI zero-shot, multi-task LLM agent, and 12 dedicated LLM agents from 6 vendor families), plus 11 fine-tuning experiments (all achieving MCCłeq0). Key findings: (1) a dedicated single-task LLM agent reduces neutral bias from 69% to 22%, improving MCC from -0.018 to 0.347 (p<0.001); (2) our results are consistent with the “Alignment Tax” (Lin et al., 2024; Wu et al., 2025) in sentiment classification: Claude Opus 4.6 exhibits 41% neutral predictions and lower recall than its budget model Haiku 4.5 (p=0.003); (3) \sim38% of dissatisfied customers are undetectable by all 12 LLMs due to administrative requests lacking emotional language; (4) Gemini 3 Flash achieves the best MCC (0.347) at 0.60/1K, over 100× cheaper than Claude Opus. We describe the three-phase production deployment and provide practitioner recommendations.
%U https://aclanthology.org/2026.acl-industry.121/
%P 1774-1782

Markdown (Informal)

[From TextBlob to LLM Agents: Sentiment Model Selection for B2B Technical Support with CSAT Ground Truth](https://aclanthology.org/2026.acl-industry.121/) (Vidigal, ACL 2026)

• From TextBlob to LLM Agents: Sentiment Model Selection for B2B Technical Support with CSAT Ground Truth (Vidigal, ACL 2026)

ACL

• Pedro Vidigal. 2026. From TextBlob to LLM Agents: Sentiment Model Selection for B2B Technical Support with CSAT Ground Truth. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 1774–1782, San Diego, California, USA. Association for Computational Linguistics.