@inproceedings{bauer-etal-2024-offensiveness,
title = "Offensiveness, Hate, Emotion and {GPT}: Benchmarking {GPT}3.5 and {GPT}4 as Classifiers on {T}witter-specific Datasets",
author = "Bauer, Nikolaj and
Preisig, Moritz and
Volk, Martin",
editor = "Kumar, Ritesh and
Ojha, Atul Kr. and
Malmasi, Shervin and
Chakravarthi, Bharathi Raja and
Lahiri, Bornini and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the Fourth Workshop on Threat, Aggression {\&} Cyberbullying @ LREC-COLING-2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.trac-1.14",
pages = "126--133",
abstract = "In this paper, we extend the work of benchmarking GPT by turning GPT models into classifiers and applying them on three different Twitter datasets on Hate-Speech Detection, Offensive Language Detection, and Emotion Classification. We use a Zero-Shot and Few-Shot approach to evaluate the classification capabilities of the GPT models. Our results show that GPT models do not always beat fine-tuned models on the tested benchmarks. However, in Hate-Speech and Emotion Detection, using a Few-Shot approach, state-of-the-art performance can be achieved. The results also reveal that GPT-4 is more sensitive to the examples given in a Few-Shot prompt, highlighting the importance of choosing fitting examples for inference and prompt formulation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bauer-etal-2024-offensiveness">
<titleInfo>
<title>Offensiveness, Hate, Emotion and GPT: Benchmarking GPT3.5 and GPT4 as Classifiers on Twitter-specific Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaj</namePart>
<namePart type="family">Bauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moritz</namePart>
<namePart type="family">Preisig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Volk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bornini</namePart>
<namePart type="family">Lahiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we extend the work of benchmarking GPT by turning GPT models into classifiers and applying them on three different Twitter datasets on Hate-Speech Detection, Offensive Language Detection, and Emotion Classification. We use a Zero-Shot and Few-Shot approach to evaluate the classification capabilities of the GPT models. Our results show that GPT models do not always beat fine-tuned models on the tested benchmarks. However, in Hate-Speech and Emotion Detection, using a Few-Shot approach, state-of-the-art performance can be achieved. The results also reveal that GPT-4 is more sensitive to the examples given in a Few-Shot prompt, highlighting the importance of choosing fitting examples for inference and prompt formulation.</abstract>
<identifier type="citekey">bauer-etal-2024-offensiveness</identifier>
<location>
<url>https://aclanthology.org/2024.trac-1.14</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>126</start>
<end>133</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Offensiveness, Hate, Emotion and GPT: Benchmarking GPT3.5 and GPT4 as Classifiers on Twitter-specific Datasets
%A Bauer, Nikolaj
%A Preisig, Moritz
%A Volk, Martin
%Y Kumar, Ritesh
%Y Ojha, Atul Kr.
%Y Malmasi, Shervin
%Y Chakravarthi, Bharathi Raja
%Y Lahiri, Bornini
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bauer-etal-2024-offensiveness
%X In this paper, we extend the work of benchmarking GPT by turning GPT models into classifiers and applying them on three different Twitter datasets on Hate-Speech Detection, Offensive Language Detection, and Emotion Classification. We use a Zero-Shot and Few-Shot approach to evaluate the classification capabilities of the GPT models. Our results show that GPT models do not always beat fine-tuned models on the tested benchmarks. However, in Hate-Speech and Emotion Detection, using a Few-Shot approach, state-of-the-art performance can be achieved. The results also reveal that GPT-4 is more sensitive to the examples given in a Few-Shot prompt, highlighting the importance of choosing fitting examples for inference and prompt formulation.
%U https://aclanthology.org/2024.trac-1.14
%P 126-133
Markdown (Informal)
[Offensiveness, Hate, Emotion and GPT: Benchmarking GPT3.5 and GPT4 as Classifiers on Twitter-specific Datasets](https://aclanthology.org/2024.trac-1.14) (Bauer et al., TRAC-WS 2024)
ACL