2025/04/05 by Túlio Sousa de Gois, de Gois, Túlio Sousa, Paloma Batista Cardoso +1 · 1 voice
Computer Science · Neuroscience · Social Sciences · #Language and cultural evolution #Natural Language Processing Techniques #Neurobiology of Language and Bilingualism
paper · doi:10.25189/2675-4916.2025.v6.n4.id861
openalex created_date 2025/10/10 · openalex publication_date 2025/12/23 · openalex updated_date 2026/07/31
Negation is a universal feature of natural languages. In Brazilian Portuguese, the most commonly used negation particle is não, which can take scope over nouns or verbs. When it takes scope over a verb, “não”can occur in three positions: pre-verbal (NEG1), double negation (NEG2), or post-verbal (NEG3), e.g., “não gosto”, “não gosto não”, “gosto não”(“I do not like it”). From a variationist perspective, these structures are different forms of expressing negation. Pragmatically, they serve distinct communicative functions, such as politeness and modal evaluation. Despite their grammatical acceptability, these forms differ in frequency. NEG1 dominates across Brazilian regions, while NEG2 and NEG3 appear more rarely, suggesting its use is contextually restricted. The low frequency of these structures challenges research, often resulting in subjective, non-generalizable interpretations of verbal negation with não. To address this, we developed negativas, a tool for automatically identifying NEG1, NEG2, and NEG3 in transcribed data. The tool’s development involved four stages: i) analyzing a dataset of 22 interviews from the Falares Sergipanos database, annotated by three linguists, ii) developing the code using the Python language and Natural Language Processing (NLP) techniques, iii) running the tool, iv) evaluating accuracy. Inter-annotator agreement, measured using Fleiss’ Kappa, was moderate (0.57). The tool identified 3,338 instances of não, classifying 2,085 as NEG1, NEG2, or NEG3, achieving a 93% success rate. However, negativas has limitations. NEG1 accounted for 91.5% of identified structures, while NEG2 and NEG3 represented 7.2% and 1.2%, respectively. The tool struggled with NEG2, misclassifying instances as overlapping structures (NEG1/NEG2/NEG3). These challenges stem from the dataset’s lack of punctuation, which in written texts, marks sentence boundaries. In spoken data, prosodic cues serve this purpose, recognized by speakers but not by the tool. This highlights the need for advancements in NLP to better handle the unique features of spoken language data.