Can I guess where you are from? Modeling dialectal morphosyntactic similarities in Brazilian Portuguese
Organizations: Universidade Federal de Alagoas Delmiro Gouveia - AL - Brazil · Universidade Federal de Sergipe São Cristóvão - SE - Brazil
Abstract
This paper investigates morphosyntactic covariation in Brazilian Portuguese (BP) to assess whether dialectal origin can be inferred from the combined behavior of linguistic variables. Focusing on four grammatical phenomena related to pronouns, correlation and clustering methods are applied to model covariation and dialectal distribution. The results indicate that correlation captures only limited pairwise associations, whereas clustering reveals speaker groupings that reflect regional dialectal patterns. Despite the methodological constraints imposed by differences in sample size requirements between sociolinguistics and computational approaches, the study highlights the importance of interdisciplinary research. Developing fair and inclusive language technologies that respect dialectal diversity outweighs the challenges of integrating these fields.
Figures & tables
| Variable | Variants |
|---|---|
| pro2P | você |
| cê | |
| tu | |
| clit2P | se |
| lhe | |
| poss2P | seu (masc.) |
| pro2P | clit2P | det-poss | poss2P |
|---|---|---|---|
| Você disse que | te comprometeu com | o art | teu projeto |
| Você disse que | te comprometeu com | Ø | teu projeto |
| Você disse que | te comprometeu com | o art | seu projeto |
| Você disse que | te comprometeu com | Ø | seu projeto |
| Você disse que | se comprometeu com | o art | teu projeto |
| Você disse que | se comprometeu com | Ø | teu projeto |
| Displacement Type | Description |
|---|---|
| Displacement 1 | UFS students born in Aracaju’s Metropolitan region (Aracaju, Nossa Senhora do Socorro, São Cristóvão, and Barra dos Coqueiros cities) and who reside there |
| Displacement 2 | UFS students born in the countryside of Sergipe who make the daily commute to UFS |
| Displacement 3 | UFS students born in the countryside of Sergipe who reside in Aracaju’s Metropolitan region |
| Displacement 4 | UFS students born in other states (predominantly Bahia and Alagoas) who currently reside in Aracaju’s Metropolitan region |
| Variable | Rules | Context |
|---|---|---|
| det-poss | [{’LEMMA’: {’NOT_IN’: [’meu’,’teu’, ’seu’, ’nosso’]}}, {’POS’: ’DET’, ’MORPH’:{’IS_SUPERSET’: [’PronType=Prs’]}}, {’POS’: ’NOUN’}] | Possessives meu , teu , seu , and nosso and inflections) in contexts where they precede nouns. |
| pro2P | [{’ORTH’: {’IN’: [’você’, ’cê’, ’tu’]}}, {’POS’: ’VERB’, ’MORPH’: {’IS_SUPERSET’: [’VerbForm=Fin’]}}] [{’ORTH’: {’IN’: [’você’, ’cê’, ’tu’]}}, {}, {’POS’: ’VERB’, ’MORPH’: {’IS_SUPERSET’: [’VerbForm=Fin’]}}] | Pronouns você , tu , and cê preceding verbs. Pronouns você , tu , and cê preceding verbs with intervening material between pronoun and verb. |
| clit2P | [{’ORTH’: {’IN’: [’te’, ’lhe’]}}, {’POS’: ’VERB’}] [{’POS’: ’VERB’}, {’ORTH’: {’IN’: [’te’, ’lhe’]}}] [{’POS’: ’VERB’}, {’IS_PUNCT’: True}, {’ORTH’: {’IN’: [’te’, ’lhe’]}}] | Pronouns te and lhe preceding verbs in proclitic position. Pronouns te and lhe following verbs in enclitic position. Pronouns te and lhe following verbs in enclitic position, connected by a punctuation mark (-). |
| poss2P | [{"LEMMA": {"IN": ["seu", "teu"]}}, {"POS": "NOUN"}] [{"POS": "NOUN"}, {"LEMMA": {"IN": ["seu", "teu"]}}] | Pronouns teu and seu (and inflections) preceding nouns. Pronouns teu and seu (and inflections) following nouns. |
| Variable | Variant | Frequency | % |
|---|---|---|---|
| pro2PS | você | 3064/3834 | 79.6 |
| cê | 770/3848 | 21.5 | |
| tu | 14/3848 | 0.4 | |
| clit2PS | te | 194/270 | 71.9 |
| se | 76/270 | 28.1 | |
| poss2PS | seu | 528/533 | 99.1 |