{"id":{"repo_id":"uic","oai_identifier":"oai:figshare.com:article/30425284"},"canonical_url":"https://search.dev.ndltd.org/etd/uic/oai:figshare.com:article/30425284","repository":{"repo_id":"uic","name":"University of Illinois - Chicago","base_url":"https://api.figshare.com/v2/oai"},"display":{"title":"Investigating Interlingual Errors to Enhance Intelligent Writing Assistants for Second Language Learners","abstract":"Language-learning apps offer convenient, low-pressure learning environments, often providing real-time feedback to users. One popular type of software is automated writing assistants (AWAs), which afford language-learning opportunities through explanatory messages in response to grammatical errors found in a given piece of text. These AWAs have been built upon advances in machine learning (ML) and natural language processing (NLP) for state-of-the-art grammatical error correction and feedback capabilities, as well as decades of research in language pedagogy investigating the optimal construction and delivery of corrective feedback. This work concerns a well-documented class of errors that often arise from a word-by-word translation from a native language to a target language -- interlingual errors. Though researchers have suggested developing targeted lessons and feedback that expose learners to incongruences between native and target languages to address these errors, few studies have investigated the effectiveness of this contrastive feedback and how it is received, especially in the context of AWAs. In this work, I seek to bridge this gap by exploring the feasibility of integrating contrastive feedback for interlingual preposition errors in an AWA. In particular, I (1) present and compare ML- and neural language model-based approaches to preposition error detection, highlighting the capabilities of ML classifiers with linguistically-informed features, (2) develop and validate a scalable technique for collecting annotations of interlingual errors, (3) propose and evaluate a statistical method for diagnosing an error as interlingual, and (4) conduct a user study investigating the effectiveness and perceptions of contrastive feedback in an AWA-like environment, finding that while contrastive feedback is not significantly more beneficial than direct feedback, it is still an effective and engaging type of feedback in treating interlingual errors.","abstract_html":"Language-learning apps offer convenient, low-pressure learning environments, often providing real-time feedback to users. One popular type of software is automated writing assistants (AWAs), which afford language-learning opportunities through explanatory messages in response to grammatical errors found in a given piece of text. These AWAs have been built upon advances in machine learning (ML) and natural language processing (NLP) for state-of-the-art grammatical error correction and feedback capabilities, as well as decades of research in language pedagogy investigating the optimal construction and delivery of corrective feedback. This work concerns a well-documented class of errors that often arise from a word-by-word translation from a native language to a target language -- interlingual errors. Though researchers have suggested developing targeted lessons and feedback that expose learners to incongruences between native and target languages to address these errors, few studies have investigated the effectiveness of this contrastive feedback and how it is received, especially in the context of AWAs. In this work, I seek to bridge this gap by exploring the feasibility of integrating contrastive feedback for interlingual preposition errors in an AWA. In particular, I (1) present and compare ML- and neural language model-based approaches to preposition error detection, highlighting the capabilities of ML classifiers with linguistically-informed features, (2) develop and validate a scalable technique for collecting annotations of interlingual errors, (3) propose and evaluate a statistical method for diagnosing an error as interlingual, and (4) conduct a user study investigating the effectiveness and perceptions of contrastive feedback in an AWA-like environment, finding that while contrastive feedback is not significantly more beneficial than direct feedback, it is still an effective and engaging type of feedback in treating interlingual errors.","abstract_has_math":false,"creators":["Natawut Monaikul (22482028)"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-08-01T00:00:00Z","date_published":"2025-08-01T00:00:00Z","updated_at":"2026-07-27T21:34:51Z","subjects":["Computer Science","Language, Linguistics"],"languages":[],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.25417/uic.30425284.v1","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Natawut Monaikul (22482028)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-08-01T00:00:00Z"]},{"key":"dc:relation","label":"Dc Relation","values":["https://figshare.com/articles/thesis/Investigating_Interlingual_Errors_to_Enhance_Intelligent_Writing_Assistants_for_Second_Language_Learners/30425284"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Science","Language, Linguistics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.25417/uic.30425284.v1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Language-learning apps offer convenient, low-pressure learning environments, often providing real-time feedback to users. One popular type of software is automated writing assistants (AWAs), which afford language-learning opportunities through explanatory messages in response to grammatical errors found in a given piece of text. These AWAs have been built upon advances in machine learning (ML) and natural language processing (NLP) for state-of-the-art grammatical error correction and feedback capabilities, as well as decades of research in language pedagogy investigating the optimal construction and delivery of corrective feedback. This work concerns a well-documented class of errors that often arise from a word-by-word translation from a native language to a target language -- interlingual errors. Though researchers have suggested developing targeted lessons and feedback that expose learners to incongruences between native and target languages to address these errors, few studies have investigated the effectiveness of this contrastive feedback and how it is received, especially in the context of AWAs. In this work, I seek to bridge this gap by exploring the feasibility of integrating contrastive feedback for interlingual preposition errors in an AWA. In particular, I (1) present and compare ML- and neural language model-based approaches to preposition error detection, highlighting the capabilities of ML classifiers with linguistically-informed features, (2) develop and validate a scalable technique for collecting annotations of interlingual errors, (3) propose and evaluate a statistical method for diagnosing an error as interlingual, and (4) conduct a user study investigating the effectiveness and perceptions of contrastive feedback in an AWA-like environment, finding that while contrastive feedback is not significantly more beneficial than direct feedback, it is still an effective and engaging type of feedback in treating interlingual errors."]},{"key":"dc:title","label":"Title","values":["Investigating Interlingual Errors to Enhance Intelligent Writing Assistants for Second Language Learners"]}]}],"canonical_facts":{"dc:creator":["Natawut Monaikul (22482028)"],"dc:date":["2025-08-01T00:00:00Z"],"dc:description":["Language-learning apps offer convenient, low-pressure learning environments, often providing real-time feedback to users. One popular type of software is automated writing assistants (AWAs), which afford language-learning opportunities through explanatory messages in response to grammatical errors found in a given piece of text. These AWAs have been built upon advances in machine learning (ML) and natural language processing (NLP) for state-of-the-art grammatical error correction and feedback capabilities, as well as decades of research in language pedagogy investigating the optimal construction and delivery of corrective feedback. This work concerns a well-documented class of errors that often arise from a word-by-word translation from a native language to a target language -- interlingual errors. Though researchers have suggested developing targeted lessons and feedback that expose learners to incongruences between native and target languages to address these errors, few studies have investigated the effectiveness of this contrastive feedback and how it is received, especially in the context of AWAs. In this work, I seek to bridge this gap by exploring the feasibility of integrating contrastive feedback for interlingual preposition errors in an AWA. In particular, I (1) present and compare ML- and neural language model-based approaches to preposition error detection, highlighting the capabilities of ML classifiers with linguistically-informed features, (2) develop and validate a scalable technique for collecting annotations of interlingual errors, (3) propose and evaluate a statistical method for diagnosing an error as interlingual, and (4) conduct a user study investigating the effectiveness and perceptions of contrastive feedback in an AWA-like environment, finding that while contrastive feedback is not significantly more beneficial than direct feedback, it is still an effective and engaging type of feedback in treating interlingual errors."],"dc:identifier":["10.25417/uic.30425284.v1"],"dc:relation":["https://figshare.com/articles/thesis/Investigating_Interlingual_Errors_to_Enhance_Intelligent_Writing_Assistants_for_Second_Language_Learners/30425284"],"dc:rights":["In Copyright"],"dc:subject":["Computer Science","Language, Linguistics"],"dc:title":["Investigating Interlingual Errors to Enhance Intelligent Writing Assistants for Second Language Learners"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T21:34:51Z"}