<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tripto-etal-2023-hansen">
    <titleInfo>
        <title>HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nafis</namePart>
        <namePart type="family">Tripto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adaku</namePart>
        <namePart type="family">Uchendu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thai</namePart>
        <namePart type="family">Le</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mattia</namePart>
        <namePart type="family">Setzu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fosca</namePart>
        <namePart type="family">Giannotti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dongwon</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Authorship Analysis, also known as stylometry, has been an essential aspect of Natural Language Processing (NLP) for a long time. Likewise, the recent advancement of Large Language Models (LLMs) has made authorship analysis increasingly crucial for distinguishing between human-written and AI-generated texts. However, these authorship analysis tasks have primarily been focused on written texts, not considering spoken texts. Thus, we introduce the largest benchmark for spoken texts - \sf HANSEN(\underlineHuman \underlineANd ai \underlineSpoken t\underlineExt be\underlineNchmark). \sf HANSEN encompasses meticulous curation of existing speech datasets accompanied by transcripts, alongside the creation of novel AI-generated spoken text datasets. Together, it comprises 17 human datasets, and AI-generated spoken texts created using 3 prominent LLMs: ChatGPT, PaLM2, and Vicuna13B. To evaluate and demonstrate the utility of \sf HANSEN, we perform Authorship Attribution (AA) &amp; Author Verification (AV) on human-spoken datasets and conducted Human vs. AI text detection using state-of-the-art (SOTA) models. While SOTA methods, such as, character n-gram or Transformer-based model, exhibit similar AA &amp; AV performance in human-spoken datasets compared to written ones, there is much room for improvement in AI-generated spoken text detection. The \sf HANSEN benchmark is available at: https://huggingface.co/datasets/HANSEN-REPO/HANSEN</abstract>
    <identifier type="citekey">tripto-etal-2023-hansen</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.916</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.916</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>13706</start>
            <end>13724</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis
%A Tripto, Nafis
%A Uchendu, Adaku
%A Le, Thai
%A Setzu, Mattia
%A Giannotti, Fosca
%A Lee, Dongwon
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F tripto-etal-2023-hansen
%X Authorship Analysis, also known as stylometry, has been an essential aspect of Natural Language Processing (NLP) for a long time. Likewise, the recent advancement of Large Language Models (LLMs) has made authorship analysis increasingly crucial for distinguishing between human-written and AI-generated texts. However, these authorship analysis tasks have primarily been focused on written texts, not considering spoken texts. Thus, we introduce the largest benchmark for spoken texts - \sf HANSEN(\underlineHuman \underlineANd ai \underlineSpoken t\underlineExt be\underlineNchmark). \sf HANSEN encompasses meticulous curation of existing speech datasets accompanied by transcripts, alongside the creation of novel AI-generated spoken text datasets. Together, it comprises 17 human datasets, and AI-generated spoken texts created using 3 prominent LLMs: ChatGPT, PaLM2, and Vicuna13B. To evaluate and demonstrate the utility of \sf HANSEN, we perform Authorship Attribution (AA) & Author Verification (AV) on human-spoken datasets and conducted Human vs. AI text detection using state-of-the-art (SOTA) models. While SOTA methods, such as, character n-gram or Transformer-based model, exhibit similar AA & AV performance in human-spoken datasets compared to written ones, there is much room for improvement in AI-generated spoken text detection. The \sf HANSEN benchmark is available at: https://huggingface.co/datasets/HANSEN-REPO/HANSEN
%R 10.18653/v1/2023.findings-emnlp.916
%U https://aclanthology.org/2023.findings-emnlp.916
%U https://doi.org/10.18653/v1/2023.findings-emnlp.916
%P 13706-13724

Markdown (Informal)

[HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis](https://aclanthology.org/2023.findings-emnlp.916) (Tripto et al., Findings 2023)

• HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis (Tripto et al., Findings 2023)

ACL

• Nafis Tripto, Adaku Uchendu, Thai Le, Mattia Setzu, Fosca Giannotti, and Dongwon Lee. 2023. HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13706–13724, Singapore. Association for Computational Linguistics.