<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nedilko-2023-team">
    <titleInfo>
        <title>TEAM BIAS BUSTERS@LT-EDI-2023: Detecting Signs of Depression with Generative Pretrained Transformers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">Nedilko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bharathi</namePart>
            <namePart type="given">R</namePart>
            <namePart type="family">Chakravarthi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">B</namePart>
            <namePart type="family">Bharathi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joephine</namePart>
            <namePart type="family">Griffith</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>
        <name type="personal">
            <namePart type="given">Paul</namePart>
            <namePart type="family">Buitelaar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes our methodology adopted to participate in the multi-class classification task under the auspices of the Third Workshop on Language Technology for Equality, Diversity, Inclusion (LT-EDI) in the Recent Advances in Natural Language Processing (RANLP) 2023 conference. The overall objective was to employ ML algorithms to detect signs of depression in English social media content, classifying each post into one of three categories: no depression, moderate depression, and severe depression. To accomplish this we utilized generative pretrained transformers (GPTs), leveraging the full-scale OpenAI API. Our strategy incorporated prompt engineering for zero-shot and few-shot learning scenarios with ChatGPT and fine-tuning a GPT-3 model. The latter approach yielded the best results which allowed us to outperform our benchmark XGBoost classifier based on character-level features on the dev set and score a macro F1 score of 0.419 on the final blind test set.</abstract>
    <identifier type="citekey">nedilko-2023-team</identifier>
    <location>
        <url>https://aclanthology.org/2023.ltedi-1.20</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>138</start>
            <end>143</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TEAM BIAS BUSTERS@LT-EDI-2023: Detecting Signs of Depression with Generative Pretrained Transformers
%A Nedilko, Andrew
%Y Chakravarthi, Bharathi R.
%Y Bharathi, B.
%Y Griffith, Joephine
%Y Bali, Kalika
%Y Buitelaar, Paul
%S Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F nedilko-2023-team
%X This paper describes our methodology adopted to participate in the multi-class classification task under the auspices of the Third Workshop on Language Technology for Equality, Diversity, Inclusion (LT-EDI) in the Recent Advances in Natural Language Processing (RANLP) 2023 conference. The overall objective was to employ ML algorithms to detect signs of depression in English social media content, classifying each post into one of three categories: no depression, moderate depression, and severe depression. To accomplish this we utilized generative pretrained transformers (GPTs), leveraging the full-scale OpenAI API. Our strategy incorporated prompt engineering for zero-shot and few-shot learning scenarios with ChatGPT and fine-tuning a GPT-3 model. The latter approach yielded the best results which allowed us to outperform our benchmark XGBoost classifier based on character-level features on the dev set and score a macro F1 score of 0.419 on the final blind test set.
%U https://aclanthology.org/2023.ltedi-1.20
%P 138-143

Markdown (Informal)

[TEAM BIAS BUSTERS@LT-EDI-2023: Detecting Signs of Depression with Generative Pretrained Transformers](https://aclanthology.org/2023.ltedi-1.20) (Nedilko, LTEDI-WS 2023)

• TEAM BIAS BUSTERS@LT-EDI-2023: Detecting Signs of Depression with Generative Pretrained Transformers (Nedilko, LTEDI-WS 2023)

ACL

• Andrew Nedilko. 2023. TEAM BIAS BUSTERS@LT-EDI-2023: Detecting Signs of Depression with Generative Pretrained Transformers. In Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion, pages 138–143, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.