<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nerujan-sarveswaran-2026-feature">
    <titleInfo>
        <title>A Feature-Fusion Ensemble Approach for Tamil Hate Speech Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sathasivam</namePart>
        <namePart type="family">Nerujan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kengatharaiyer</namePart>
        <namePart type="family">Sarveswaran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kengatharaiyer</namePart>
            <namePart type="family">Sarveswaran</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ashwini</namePart>
            <namePart type="family">Vaidya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Detecting online toxicity in morphologically rich, low-resource languages like Tamil remains a major computational challenge. Standard transformer models often struggle with sub-word fragmentation, which can dilute the semantic intensity of regional insults and out-of-vocabulary slang. To mitigate this limitation, we train a multi-layer hybrid framework that fuses the deep contextual representations of L3Cube-TamilBERT with the character-level robustness of FastText embeddings. Our architecture leverages Last-4 Layers averaging and a dual pooling strategy (Mean + Max) to capture both global sentence intent and extract high-activation spikes of offensive cues typically lost in single layer representations. Experiments show that this hybrid model achieves a Macro-F1 of 0.7883, notably enhancing Hate Recall (0.7503) for detection of offensive content. Additionally, as reported by other studies, stacking ensemble achieves peak hate precision (0.9296), providing a high accuracy alternative for moderation scenarios requiring minimal false positives. By combining deep contextual hidden states with FastText embeddings, the proposed feature-fusion ensemble approach with multi-layer hybrid framework approach establishes a new benchmark for hate speech detection for Tamil.</abstract>
    <identifier type="citekey">nerujan-sarveswaran-2026-feature</identifier>
    <identifier type="doi">10.63317/2us8ubrf4jvi</identifier>
    <location>
        <url>https://aclanthology.org/2026.chipsal-1.18/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>190</start>
            <end>197</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Feature-Fusion Ensemble Approach for Tamil Hate Speech Detection
%A Nerujan, Sathasivam
%A Sarveswaran, Kengatharaiyer
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%S Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F nerujan-sarveswaran-2026-feature
%X Detecting online toxicity in morphologically rich, low-resource languages like Tamil remains a major computational challenge. Standard transformer models often struggle with sub-word fragmentation, which can dilute the semantic intensity of regional insults and out-of-vocabulary slang. To mitigate this limitation, we train a multi-layer hybrid framework that fuses the deep contextual representations of L3Cube-TamilBERT with the character-level robustness of FastText embeddings. Our architecture leverages Last-4 Layers averaging and a dual pooling strategy (Mean + Max) to capture both global sentence intent and extract high-activation spikes of offensive cues typically lost in single layer representations. Experiments show that this hybrid model achieves a Macro-F1 of 0.7883, notably enhancing Hate Recall (0.7503) for detection of offensive content. Additionally, as reported by other studies, stacking ensemble achieves peak hate precision (0.9296), providing a high accuracy alternative for moderation scenarios requiring minimal false positives. By combining deep contextual hidden states with FastText embeddings, the proposed feature-fusion ensemble approach with multi-layer hybrid framework approach establishes a new benchmark for hate speech detection for Tamil.
%R 10.63317/2us8ubrf4jvi
%U https://aclanthology.org/2026.chipsal-1.18/
%U https://doi.org/10.63317/2us8ubrf4jvi
%P 190-197

Markdown (Informal)

[A Feature-Fusion Ensemble Approach for Tamil Hate Speech Detection](https://aclanthology.org/2026.chipsal-1.18/) (Nerujan & Sarveswaran, CHiPSAL 2026)

• A Feature-Fusion Ensemble Approach for Tamil Hate Speech Detection (Nerujan & Sarveswaran, CHiPSAL 2026)

ACL

• Sathasivam Nerujan and Kengatharaiyer Sarveswaran. 2026. A Feature-Fusion Ensemble Approach for Tamil Hate Speech Detection. In Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026), pages 190–197, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).