@inproceedings{higdon-etal-2025-predictability,
title = "Predictability Effects of {S}panish-{E}nglish Code-Switching: A Directionality and Part of Speech Analysis",
author = "Higdon, Josh and
Pagliai, Valeria and
Liu, Zoey",
editor = "Chen, Xinying and
Wang, Yaqin",
booktitle = "Proceedings of the Third Workshop on Quantitative Syntax (QUASY, SyntaxFest 2025)",
month = aug,
year = "2025",
address = "Ljubljana, Slovenia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.quasy-1.11/",
pages = "83--89",
ISBN = "979-8-89176-293-0",
abstract = "Research on code-switching (CS), the spontaneous alternation between two or more languages within a discourse, remains relatively new and often limited by the use of elicited production tasks, with some exceptions leveraging naturalistic corpora. This study analyses the effects of language directionality and part-of-speech (POS) tags on Spanish-English CS production between corpus modalities and speech communities. We use data from two spoken corpora: Miami Bangor Corpus (MBC; N = 261,711) and Spanish in Texas Corpus (STC; N = 416,784), as well as the written LinCE Corpus (N=278,093). Bootstrap analyses indicate that Spanish serves as the matrix language (i.e., the most used) for MBC and LinCE, while English is for STC. Logistic regression analyses show that the particle-coordinating conjunction combination was the strongest POS predictor of a CS. The results suggest that corpus modality and the speech community affect matrix language proportions and that both previously attested and unseen POS combinations modulate the production of Spanish-English CS."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="higdon-etal-2025-predictability">
<titleInfo>
<title>Predictability Effects of Spanish-English Code-Switching: A Directionality and Part of Speech Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Higdon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valeria</namePart>
<namePart type="family">Pagliai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoey</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Quantitative Syntax (QUASY, SyntaxFest 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaqin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Ljubljana, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-293-0</identifier>
</relatedItem>
<abstract>Research on code-switching (CS), the spontaneous alternation between two or more languages within a discourse, remains relatively new and often limited by the use of elicited production tasks, with some exceptions leveraging naturalistic corpora. This study analyses the effects of language directionality and part-of-speech (POS) tags on Spanish-English CS production between corpus modalities and speech communities. We use data from two spoken corpora: Miami Bangor Corpus (MBC; N = 261,711) and Spanish in Texas Corpus (STC; N = 416,784), as well as the written LinCE Corpus (N=278,093). Bootstrap analyses indicate that Spanish serves as the matrix language (i.e., the most used) for MBC and LinCE, while English is for STC. Logistic regression analyses show that the particle-coordinating conjunction combination was the strongest POS predictor of a CS. The results suggest that corpus modality and the speech community affect matrix language proportions and that both previously attested and unseen POS combinations modulate the production of Spanish-English CS.</abstract>
<identifier type="citekey">higdon-etal-2025-predictability</identifier>
<location>
<url>https://aclanthology.org/2025.quasy-1.11/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>83</start>
<end>89</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predictability Effects of Spanish-English Code-Switching: A Directionality and Part of Speech Analysis
%A Higdon, Josh
%A Pagliai, Valeria
%A Liu, Zoey
%Y Chen, Xinying
%Y Wang, Yaqin
%S Proceedings of the Third Workshop on Quantitative Syntax (QUASY, SyntaxFest 2025)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Ljubljana, Slovenia
%@ 979-8-89176-293-0
%F higdon-etal-2025-predictability
%X Research on code-switching (CS), the spontaneous alternation between two or more languages within a discourse, remains relatively new and often limited by the use of elicited production tasks, with some exceptions leveraging naturalistic corpora. This study analyses the effects of language directionality and part-of-speech (POS) tags on Spanish-English CS production between corpus modalities and speech communities. We use data from two spoken corpora: Miami Bangor Corpus (MBC; N = 261,711) and Spanish in Texas Corpus (STC; N = 416,784), as well as the written LinCE Corpus (N=278,093). Bootstrap analyses indicate that Spanish serves as the matrix language (i.e., the most used) for MBC and LinCE, while English is for STC. Logistic regression analyses show that the particle-coordinating conjunction combination was the strongest POS predictor of a CS. The results suggest that corpus modality and the speech community affect matrix language proportions and that both previously attested and unseen POS combinations modulate the production of Spanish-English CS.
%U https://aclanthology.org/2025.quasy-1.11/
%P 83-89
Markdown (Informal)
[Predictability Effects of Spanish-English Code-Switching: A Directionality and Part of Speech Analysis](https://aclanthology.org/2025.quasy-1.11/) (Higdon et al., Quasy-SyntaxFest 2025)
ACL