Native Dialect Influence Detection (NDID) differentiating between Mexican and Peninsular L1 Spanish in L2 English

The current investigation addresses a vital lacuna in forensic author-ship studies, and more concretely, in Native Language Influence Detection (NLID)research: narrowing down a speaker’s native dialect instead of only their nativelanguage (L1), which might not be enough when carrying out sociolinguistic pro-filing tasks. Native Dialect Influence Detection (NDID), the focus of our study,can thus greatly aid at the investigative level. We approach this topic by pro-viding a comprehensive analysis of linguistic features that serve to identify twonon-contact dialects of L1 Spanish (i.e., Mexican and Peninsular varieties) whendealing with data written in L2 English, which come from Tripadvisor. Our mainaim is to investigate if an author’s L2 features can point to their L1 native di-alect, rather than only to their native language. Findings point to L1 dialectaltransfer of punctuation signs, adjectives of affect, and intensifiers: these linguisticfeatures, even when expressed in an L2, show a culturally bound use. Addition-ally, we implemented an automatic classifier that achieved an accuracy of 69% incategorizing test data, using only linguistic features that have explanatory powerand can aid linguistic theory. This is key for explainability in the forensic con-text, which Native Language Identification (NLI) studies tend to neglect (Kingston2019). Results show that L1 Spanish dialects can be differentiated by analyzing L2English text, pointing to NDID as a fertile approach for narrowing down candidateL1 dialects of a language when analyzing L2 data.