<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aravinthakshan-etal-2026-human">
    <titleInfo>
        <title>Human Agreement and Return Association Are Not Interchangeable Criteria</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">A</namePart>
        <namePart type="given">S</namePart>
        <namePart type="family">Aravinthakshan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Laven</namePart>
        <namePart type="family">Srivastava</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Harsh</namePart>
        <namePart type="family">Nandwani</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 11th Workshop on Financial Technology and Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jimin</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yongjae</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sophia</namePart>
            <namePart type="family">Ananiadou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hsin-Hsi</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hiroya</namePart>
            <namePart type="family">Takamura</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chung-Chi</namePart>
            <namePart type="family">Chen</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">979-8-89176-466-8</identifier>
    </relatedItem>
    <abstract>Financial NLP has a standard workflow: validate a sentiment tool against human labels, then trust it to extract market signal. This assumes the two evaluations measure the same thing. We test that assumption in a setting where both can be measured at once: a corpus of securities class actions (2002–2025) linking 70,500 X[formerly Twitter] messages to abnormal stock returns, with a single-annotator human labelled gold sample. Running five instruments (VADER, Loughran–McDonald, FinBERT, Twitter-RoBERTa, and an LLM annotator) through one identical pipeline, we find that the relationship between construct and predictive validity depends on the sampling convention and score representation. Under conventional method-specific sampling, human agreement aligns more closely with graded same-day associations than with one-day leads. On a fixed-n panel, however, agreement has similar graded rank correlations at both horizons, while the coarse ordering remains weak. Benchmark agreement therefore establishes semantic validity but does not by itself determine predictive rankings. In a conversation that is 17.6% spam, message volume predicts neither market damage nor settlement size.</abstract>
    <identifier type="citekey">aravinthakshan-etal-2026-human</identifier>
    <location>
        <url>https://aclanthology.org/2026.finnlp-1.55/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>667</start>
            <end>680</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Human Agreement and Return Association Are Not Interchangeable Criteria
%A Aravinthakshan, A. S.
%A Srivastava, Laven
%A Nandwani, Harsh
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F aravinthakshan-etal-2026-human
%X Financial NLP has a standard workflow: validate a sentiment tool against human labels, then trust it to extract market signal. This assumes the two evaluations measure the same thing. We test that assumption in a setting where both can be measured at once: a corpus of securities class actions (2002–2025) linking 70,500 X[formerly Twitter] messages to abnormal stock returns, with a single-annotator human labelled gold sample. Running five instruments (VADER, Loughran–McDonald, FinBERT, Twitter-RoBERTa, and an LLM annotator) through one identical pipeline, we find that the relationship between construct and predictive validity depends on the sampling convention and score representation. Under conventional method-specific sampling, human agreement aligns more closely with graded same-day associations than with one-day leads. On a fixed-n panel, however, agreement has similar graded rank correlations at both horizons, while the coarse ordering remains weak. Benchmark agreement therefore establishes semantic validity but does not by itself determine predictive rankings. In a conversation that is 17.6% spam, message volume predicts neither market damage nor settlement size.
%U https://aclanthology.org/2026.finnlp-1.55/
%P 667-680

Markdown (Informal)

[Human Agreement and Return Association Are Not Interchangeable Criteria](https://aclanthology.org/2026.finnlp-1.55/) (Aravinthakshan et al., FinNLP 2026)

• Human Agreement and Return Association Are Not Interchangeable Criteria (Aravinthakshan et al., FinNLP 2026)

ACL

• A S Aravinthakshan, Laven Srivastava, and Harsh Nandwani. 2026. Human Agreement and Return Association Are Not Interchangeable Criteria. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 667–680, Budapest, Hungary. Association for Computational Linguistics.