<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-2024-leveraging">
    <titleInfo>
        <title>Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Linda</namePart>
        <namePart type="family">Zeng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">James</namePart>
            <namePart type="family">Hale</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kushal</namePart>
            <namePart type="family">Chawla</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Muskan</namePart>
            <namePart type="family">Garg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Code-mixing (CM), where speakers blend languages within a single expression, is prevalent in multilingual societies but poses challenges for natural language processing due to its complexity and limited data. We propose using a large language model to generate synthetic CM data, which is then used to enhance the performance of task-specific models for CM sentiment analysis. Our results show that in Spanish-English, synthetic data improved the F1 score by 9.32%, outperforming previous augmentation techniques. However, in Malayalam-English, synthetic data only helped when the baseline was low; with strong natural data, additional synthetic data offered little benefit. Human evaluation confirmed that this approach is a simple, cost-effective way to generate natural-sounding CM sentences, particularly beneficial for low baselines. Our findings suggest that few-shot prompting of large language models is a promising method for CM data augmentation and has significant impact on improving sentiment analysis, an important element in the development of social influence systems.</abstract>
    <identifier type="citekey">zeng-2024-leveraging</identifier>
    <location>
        <url>https://aclanthology.org/2024.sicon-1.6</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>85</start>
            <end>101</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis
%A Zeng, Linda
%Y Hale, James
%Y Chawla, Kushal
%Y Garg, Muskan
%S Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zeng-2024-leveraging
%X Code-mixing (CM), where speakers blend languages within a single expression, is prevalent in multilingual societies but poses challenges for natural language processing due to its complexity and limited data. We propose using a large language model to generate synthetic CM data, which is then used to enhance the performance of task-specific models for CM sentiment analysis. Our results show that in Spanish-English, synthetic data improved the F1 score by 9.32%, outperforming previous augmentation techniques. However, in Malayalam-English, synthetic data only helped when the baseline was low; with strong natural data, additional synthetic data offered little benefit. Human evaluation confirmed that this approach is a simple, cost-effective way to generate natural-sounding CM sentences, particularly beneficial for low baselines. Our findings suggest that few-shot prompting of large language models is a promising method for CM data augmentation and has significant impact on improving sentiment analysis, an important element in the development of social influence systems.
%U https://aclanthology.org/2024.sicon-1.6
%P 85-101

Markdown (Informal)

[Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis](https://aclanthology.org/2024.sicon-1.6) (Zeng, SICon 2024)

• Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis (Zeng, SICon 2024)

ACL

• Linda Zeng. 2024. Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis. In Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024), pages 85–101, Miami, Florida, USA. Association for Computational Linguistics.