[
    {
        "id": "osp-17069",
        "type": "article-journal",
        "title": "From Abusive Language Classification to Sequence Labeling Identification",
        "author": [
            {
                "family": "Zampieri",
                "given": "Nicolas"
            },
            {
                "family": "Lopez",
                "given": "Ignacio"
            },
            {
                "family": "Girard",
                "given": "Manon"
            },
            {
                "family": "Auguste",
                "given": "Jeremy"
            }
        ],
        "URL": "https://omanscience.com/en/articles/from-abusive-language-classification-to-sequence-labeling-identification",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Industrial content moderation must process massive message streams under tight latency constraints, yet most abusive language (AL) detection systems rely on sentence-level classification (ALC), which neither localizes abusive spans nor identifies who is targeted. We define Abusive Language Identification (ALI) as a sequence-labeling task that jointly extracts AL spans and target mentions, and assess whether this approach can be used for text moderation. On a pilot corpus drawn from a production moderation pipeline, we compare ALI with ALC on cross-domain generalization and implicit abuse, and we also evaluate AL and target span detection. ALI remains competitive with ALC while providing localized outputs for moderators, with a modest and configuration-sensitive advantage on implicit abuse. Exact AL boundaries and target spans remain difficult to recover. We complement this comparison with a qualitative analysis and discuss perspectives on complete target--span linking and on structured benchmarks for ALI."
    }
]