@inproceedings{duarte-etal-2026-consumerbr,
    title = "{C}onsumer{BR}: A Large-Scale Corpus of Consumer Complaints in {B}razilian {P}ortuguese",
    author = "Duarte, Luis A.  and
      Giacomin, Pedro  and
      Bispo, Vit{\'o}ria  and
      Silva, Mariana O.  and
      Pereira, Adriano C. M.  and
      Pappa, Gisele L.",
    editor = "Souza, Marlo  and
      de-Dios-Flores, Iria  and
      Santos, Diana  and
      Freitas, Larissa  and
      Souza, Jackson Wilke da Cruz  and
      Ribeiro, Eug{\'e}nio",
    booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
    month = apr,
    year = "2026",
    address = "Salvador, Brazil",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-dnd/2026.propor-1.66/",
    pages = "667--675",
    ISBN = "979-8-89176-387-6",
    abstract = "We present ConsumerBR, a large-scale corpus of consumer complaints and company responses in Brazilian Portuguese, compiled from publicly available data on the Consumidor.gov.br platform. The corpus comprises over 3.1 million consumer{--}company interactions collected between 2021 and 2025 and combines anonymized textual content with rich structured metadata, including temporal information, complaint outcomes, and consumer satisfaction indicators. We describe a data collection strategy tailored to the platform{'}s dynamic interface, a preprocessing pipeline that includes response clustering to identify template-based replies, and a hybrid anonymization approach designed to mitigate privacy risks. We also provide a detailed statistical characterization of the corpus, highlighting its scale, coverage, and distributional properties. ConsumerBR is publicly available for research purposes and supports a wide range of applications, including complaint analysis, sentiment modeling, dialogue and response generation, and preference-based evaluation."
}