Beyond Language Barriers - Allowing Multiple Languages in Postsecondary Chemistry Classes Through Multilingual Machine Learning

Aug 3, 2026

Upload by Miles

Students who learn the language of instruction as an additional language form a heterogeneous group shaped by diverse linguistic and cultural backgrounds, which increases classroom diversity. While engaging in chemistry, these learners encounter compounded language-related barriers that can limit participation and equitable assessment. The work proposes and validates approaches enabling undergraduate chemistry students to complete formative assessments in their preferred language. It evaluates translation tools and multilingual machine learning models to assess written reasoning across languages, supporting equal access.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Keywords

Introduction

Beyond Language Barriers: Allowing Multiple Languages in Postsecondary Chemistry Classes Through Multilingual Machine Learning Paul P. Martin1 · Nicole Graulich1 Accepted: 16 November 2023 / Published online: 14 February 2024 © The Author(s) 2024 Abstract Students who learn the language of instruction as an additional language represent a heterogeneous group with varying linguistic and cultural backgrounds, contributing to classroom diversity. Because of the manifold challenges these students encounter while learning the language of instruction, additional barriers arise for them when engaging in chemistry classes. Adapting teaching practices to the language skills of these students, for instance, in formative assessments, is essential to promote equity and inclusivity in chemistry learning. For this reason, novel educational practices are needed to meet each student’s unique set of language capabilities, irrespective of course size. In this study, we propose and validate several approaches to allow undergraduate chemistry students who are not yet fluent in the language of instruction to complete a formative assessment in their preferred language. A technically easy-to-implement option for instructors is to use translation tools to translate students’ reasoning in any language into the instructor’s language. Besides, instructors could also establish multilingual machine learning models capable of automatically analyzing students’ reasoning regardless of the applied language. Herein, we evaluated both opportunities by comparing the reliability of three translation tools and determining the degree to which multilingual machine learning models can simultaneously assess written arguments in different languages. The findings illustrate opportunities to apply machine learning for analyzing students’ reasoning in multiple languages, demonstrating the potential of such techniques in ensuring equal access for learners of the language of instruction. Keywords Equity · Language inclusivity · Formative assessment · Machine learning · Natural language processing Introduction Linguistic diversity is increasing in science subjects like chemistry, so the language of instruction does not necessarily correspond to a student’s first language. Students who learn the language of instruction as an additional language face unique challenges in language acquisition, science learning, and the intersection of both (del Rosario Basterra et al., 2011 ; Lee & Fradd, 1998) . Therefore, further barriers arise for them to actively participate in chemistry classes (Deng & Flynn, 2023) . * Nicole Graulich [Nicole.Graulich@didaktik.chemie.uni-giessen.de](Nicole.Graulich@didaktik.chemie.uni-giessen.de) Paul P. Martin [Paul.Martin@didaktik.chemie.uni-giessen.de](Paul.Martin@didaktik.chemie.uni-giessen.de) 1 Institute of Chemistry Education, Justus-Liebig-University, Heinrich-Buff-Ring 17, 35392 Giessen, Germany So far, much research has focused on students who learn English as an additional language (Eng+) . These Eng+ students represent a heterogeneous group with diverse linguistic backgrounds, different prior opportunities in learning English, and varying experiences in communicating in another language (Deng & Flynn, 2023 ; Deng et al., 2022 ; Flores & Smith, 2013) . Although these Eng+ students may possess strong content knowledge, they may lack the fluency to fully express their knowledge in English (Deng & Flynn, 2023; Deng et al., 2022 ; Flores & Smith, 2013; Lyon et al. , 2012 ; Swanson et al. , 2014) . This language barrier can hinder effective communication, impede the exchange of ideas, and potentially exclude valuable contributions from Eng+ students (Deng & Flynn, 2023 ; Deng et al. , 2022) . Additionally, Eng+ students may experience linguistic insecurity, which involves feelings of anxiety about their English language usage (Deng & Flynn, 2023) . In educational settings such as chemistry classes, students taught in a diffe

FAQs

Why do additional-language learners face barriers in chemistry classes?

Because learning the language of instruction introduces extra challenges for understanding, communicating, and constructing evidence-based arguments in domain-specific contexts.

What approaches does the study propose for formative assessments in students’ preferred languages?

It evaluates (1) translation tools that translate students’ reasoning into the instructor’s language and (2) multilingual machine learning models that analyze written reasoning regardless of the language used.

How were translation tools and multilingual machine learning models evaluated?

The study compares the reliability of three translation tools and measures how well multilingual machine learning models can assess written arguments written in different languages.

Aug 3, 2026

Upload by Miles