cover
Contact Name
Achmad Fawaid
Contact Email
achmad_fawaid.linguistik@upnjatim.ac.id
Phone
+6282318007953
Journal Mail Official
khatulistiwanarasi@gmail.com
Editorial Address
Dusun Krajan, RT 015 / RW 007 Desa Karanganyar, Kecamatan Paiton, Kabupaten Probolinggo, Provinsi Jawa Timur, Kodepos 67291
Location
Kab. probolinggo,
Jawa timur
INDONESIA
Indonesian Journal of Computational Language Studies
ISSN : -     EISSN : 31637884     DOI : -
Core Subject :
Indonesian Journal of Computational Language Studies is a double blind peer-reviewed scholarly journal that publishes original research articles and critical studies at the intersection of language, computation, and data-driven methodologies. This journal is published quarterly as a platform for the dissemination of theoretical, empirical, and interdisciplinary findings that explore how computational approaches contribute to the analysis, modeling, and understanding of linguistic phenomena. It addresses a broad range of topics, including but not limited to computational linguistics, natural language processing, corpus linguistics, language modeling, machine learning for language analysis, discourse and text mining, digital humanities, language technologies, and computational approaches to language use across social, cultural, and digital contexts.
Arjuna Subject : -
Articles 18 Documents
Small models, many languages: parameter-efficient adaptation of multilingual language models for low-resource Indonesian languages Ainul Hadziqi
Indonesian Journal of Computational Language Studies Vol. 1 No. 2 (2026): Large language models, linguistic diversity, and responsible NLP in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijcl.v1i2.916

Abstract

Background: Multilingual language models have expanded computational access to many languages, yet Indonesian local languages remain unevenly represented in corpora, benchmarks, and adaptation pipelines despite Indonesia’s exceptional linguistic diversity. Objective: This study examines how parameter-efficient adaptation can support small multilingual language models for low-resource Indonesian languages by treating corpus adequacy, source provenance, language coverage, and evaluation readiness as central methodological conditions. Method: Using a corpus-level research design, this study maps 20 public source-level items consisting of task datasets, benchmark resources, documentation, registry infrastructure, supplementary corpus portals, and model-context collections for Indonesian and selected local languages. Results: The findings show that task-ready datasets form the strongest part of the corpus frame, while benchmarking, reproducibility, and auxiliary corpus layers remain less evenly distributed. Language coverage is stratified, with Javanese and Sundanese occupying stronger cross-task positions, while Acehnese, Ngaju, Bima, Toba Batak, and Ambonese Malay are better treated as focused transfer-stress cases. Implication: These patterns indicate that parameter-efficient fine-tuning should not be interpreted through model efficiency alone, because adaptation gains remain bounded by corpus distribution and language-specific evidence. Novelty: The novelty of this study lies in repositioning PEFT for Indonesian local languages as a corpus-dependent multilingual adaptation problem rather than a purely architectural optimization problem
Who gets represented by Indonesian AI? measuring regional, gender, and sociolinguistic bias in large language models Mohammad Anis Sumadi
Indonesian Journal of Computational Language Studies Vol. 1 No. 2 (2026): Large language models, linguistic diversity, and responsible NLP in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijcl.v1i2.917

Abstract

Background: Indonesia’s regional, gendered, and sociolinguistic diversity raises a critical question about whether large language models represent Indonesian identities with equal specificity, agency, and legitimacy in computational discourse. Objective: This study aims to examine how Indonesian-facing large language models generate representations of regions, gender markers, occupations, and language varieties under controlled prompt conditions. Method: Using a prompt-based audit design, this study analyses 42 prompt units divided into regional, gender-counterfactual, and sociolinguistic conditions, with coding focused on visibility, specificity, agency, competence, register alignment, semantic stability, and language shifting. Results: The findings indicate that regional representation is uneven: some regions are profiled through professional competence, while others are rendered through generic neutrality, cultural tokenisation, peripheral framing, or national homogenisation. Gendered outputs show partial professional parity, but male-coded subjects receive stronger leadership and technical authority, whereas female-coded subjects are more often associated with care, affect, and relational labour. Implication: Sociolinguistic robustness is strongest in formal Indonesian, more adaptive in colloquial Indonesian, and less stable in local-language conditions, where semantic drift, code-mixing, and defaulting to Indonesian appear. Novelty: This study contributes an intersectional audit framework that reframes Indonesian AI bias as a problem of regional visibility, gendered agency, and sociolinguistic legitimacy across culturally stratified AI systems in multilingual Indonesia today.
Listening to the archipelago: automatic speech recognition, accent variation, and the unequal modeling of Indonesian voices Imam Masrur
Indonesian Journal of Computational Language Studies Vol. 1 No. 3 (2026): Computational sociolinguistics, speech, and digital discourse in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijcl.v1i3.1026

Abstract

Background: Indonesia’s archipelagic linguistic ecology makes automatic speech recognition (ASR) a problem of sociotechnical representation, because spoken Indonesian is shaped by regional accent, local-language influence, code-switching, and uneven access to standardized speech resources. Objective: This study examines how Indonesian ASR resources, evaluation practices, and model documentation make regional and accent-varied voices differentially visible, testable, and interpretable. Method: This study applies a corpus-based ASR audit to 18 public and verifiable corpus items, combining archipelagic representation analysis, accent-sensitive error-evaluation readiness, and sociotechnical visibility assessment. Results: The corpus shows that regional-language resources are more visible than dialectal Indonesian speech directly suitable for accent-sensitive ASR evaluation. Error-evaluation readiness is uneven because several items require transcript alignment, utterance segmentation, metadata enrichment, or model-output comparison before reliable subgroup analysis can be conducted. Sociotechnical visibility is fragmented across direct speech evidence, preprocessing-dependent materials, literature-mediated findings, and model-opaque documentation. Implication: These findings reposition Indonesian ASR fairness as a question of audibility, evaluability, and linguistic justice rather than aggregate transcription accuracy alone. Novelty: This study contributes an archipelagic framework for assessing unequal machine listening in Indonesian ASR by integrating corpus representation, evaluation readiness, and sociotechnical visibility.
Code-switching as a computational problem: modeling Indonesian–English digital talk beyond monolingual assumptions Devita Septian Dwi Hidayati
Indonesian Journal of Computational Language Studies Vol. 1 No. 3 (2026): Computational sociolinguistics, speech, and digital discourse in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijcl.v1i3.1027

Abstract

Background: Indonesian–English digital talk increasingly exposes the limits of language technologies that assume stable monolingual input, because switch-points often carry stance, affect, technical meaning, platform practice, and identity across compact social media utterances. Objective: This study examines how Indonesian–English code-switching can be modeled as a computational problem without reducing mixed-language digital utterances to noise, error, or preprocessing residue. Method: Using a corpus-based qualitative-computational design, this study analyzes 15 coded public digital text records through token-level language identification, switch-point mapping, normalization–translation alignment, and pragmatic-computational risk coding. Results: Code-switching appears as structured multilingual practice, with English segments functioning as evaluative phrases, technical labels, platform commands, fandom markers, and discourse-sequence devices within Indonesian frames. Normalization and translation are shown to be interpretive operations, because full correction or translation may flatten sentiment scope, register, and locally meaningful hybrid forms. Monolingual processing risks forced single-language labeling, technical mistranslation, discourse-sequence loss, and representational distortion for multilingual users. Implication: These findings reposition computational adequacy as a question of meaning preservation, not merely model accuracy or benchmark coverage in a low-resource Indonesian digital context for language technologies. Novelty: This study offers an integrated framework that links linguistic switching structure, preprocessing risk, and accountable multilingual NLP representation.
Detecting harm in context: toxicity, politeness, and cultural pragmatics in Indonesian social media NLP M. Rifa Jamaludin Nasir
Indonesian Journal of Computational Language Studies Vol. 1 No. 3 (2026): Computational sociolinguistics, speech, and digital discourse in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijcl.v1i3.1028

Abstract

Background: Indonesian social media toxicity detection remains difficult because harmful meaning is often produced through profanity, indirectness, ridicule, code-mixing, identity reference, and culturally situated politeness rather than through abusive vocabulary alone. Objective: This study examines how toxicity, politeness, and cultural pragmatics interact in Indonesian social media NLP annotation and asks what contextual evidence is required to distinguish abuse, hate speech, satire, criticism, and banter. Method: Using 60 anonymised Indonesian Twitter/X items from a public multi-label hate speech and abusive-language corpus, this study applies a mixed computational-pragmatic design combining source labels with manual interpretation of target, severity, facework, contextual validation, and risk. Results: Findings show that toxicity classes are evenly distributed, but target, domain, and severity differentiate surface abuse from identity-targeted harm. Facework cues such as direct address, laughter, ridicule, and abusive labels appear unevenly across toxicity classes, demonstrating that politeness and impoliteness cannot be inferred from lexical toxicity. Cultural-pragmatic coding shows that religion, ethnicity, gender, platform traces, political indexing, and local-language ambiguity require contextual validation before model outputs can be treated as reliable. Implication: Indonesian NLP moderation should combine classification with pragmatic annotation. Novelty: This study reframes toxicity detection as culturally grounded, target-aware, and pragmatically validated harm interpretation.
From slang to signal: tracking youth language change in Indonesian digital platforms through diachronic word embeddings Almaidah
Indonesian Journal of Computational Language Studies Vol. 1 No. 3 (2026): Computational sociolinguistics, speech, and digital discourse in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijcl.v1i3.1029

Abstract

Background: Indonesian youth slang increasingly circulates through digital platforms where lexical innovation, identity performance, meme culture, and code-mixed interaction reshape everyday meaning. Objective: This study examines how youth slang in Indonesian digital platforms can be tracked as semantic movement through diachronic word embeddings and contextual sociolinguistic validation. Method: Using public, dateable, and verifiable corpus materials, this study maps slang-bearing units across platform contexts, classifies semantic movement patterns, and validates embedding-oriented interpretation through concordance-based coding. Results: Findings show that status and identity specialization forms a dominant semantic pattern, followed by evaluative resemanticization, meme-context volatility, and pragmatic stance stabilization. Results also indicate that short-video and meme circulation privilege volatile intertextual meanings, whereas self-presentation contexts foreground slang related to attractiveness, hierarchy, persona, and social value. Contextual validation demonstrates that many slang meanings remain interactionally contingent, requiring surrounding discourse before computational shifts can be interpreted as sociolinguistically meaningful. Implication: This study shows that computational modelling of slang requires platform-sensitive interpretation to avoid reducing youth language change to frequency, novelty, or vector movement alone. Novelty: This study contributes a diachronic, corpus-assisted, and sociolinguistically grounded framework for analysing Indonesian youth slang as a measurable signal of digital semantic change.
Emotion in many registers: computational modeling of affect, irony, and public sentiment in Indonesian online discourse Ivan Riyadi
Indonesian Journal of Computational Language Studies Vol. 1 No. 3 (2026): Computational sociolinguistics, speech, and digital discourse in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijcl.v1i3.1030

Abstract

Background: Indonesian online discourse increasingly circulates emotion, irony, and public sentiment through civic complaint, protest symbolism, electoral distrust, misinformation correction, and transnational fandom conflict, making polarity-based sentiment analysis insufficient for culturally situated interpretation. Objective: This study examines how affective meaning is organized across registers and how irony, sarcasm, and pragmatic reversal reshape computational readings of Indonesian public sentiment. Method: This study applies corpus-based computational discourse analysis to 22 publicly verifiable corpus items, combining register-sensitive affect coding, irony auditing, and model–discourse misalignment analysis. Results: Civic-service complaint forms the largest affective register, showing that technical or bureaucratic failure is often transformed into public judgment of institutional competence. Irony and sarcasm operate as pragmatic filters that destabilize literal sentiment, especially through mock praise, rhetorical alarm, humorous ridicule, and group-directed antagonism. Model–discourse misalignment appears most strongly where sentiment depends on register, context, multimodal symbolism, or culturally embedded inference rather than lexical polarity alone. Implication: These findings suggest that Indonesian affective modeling requires interpretive validation alongside computational classification. Novelty: This study contributes a register-sensitive framework that integrates affect, irony, sentiment, and model-error interpretation within Indonesian computational discourse analysis.
Political talk at scale: argument mining, stance detection, and polarization in Indonesian electoral conversations Hasanudin
Indonesian Journal of Computational Language Studies Vol. 1 No. 3 (2026): Computational sociolinguistics, speech, and digital discourse in Indonesia
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/ijcl.v1i3.1031

Abstract

Background: Indonesian electoral conversations increasingly unfold through large-scale digital interaction, where political judgment is shaped not only by sentiment but also by argumentative claims, target-specific stances, institutional distrust, and polarizing boundary-making. Objective: This study examines how argument mining, stance detection, and polarization analysis can explain the organization of Indonesian electoral discourse during the 2024 presidential election cycle. Method: This study applies a corpus-assisted computational discourse design to 240 coded public electoral conversation segments drawn from official debate materials, transcript sources, institutional documents, and platform-based political commentary. Results: Findings show that policy-based reasoning, candidate evaluation, institutional legitimacy, identity boundary-making, and platform-information concerns structure electoral arguments in distinct ways. Target-aware stance analysis reveals that support, opposition, and ambivalence acquire political meaning only when attached to candidates, institutions, policy issues, opponents, or digital actors. Polarization appears as a layered discursive configuration involving issue conflict, affective hostility, identity boundaries, institutional distrust, and platform-mediated antagonism. Implication: This study demonstrates that Indonesian electoral polarization cannot be adequately inferred from sentiment polarity alone. Novelty: This study contributes an integrated framework that connects argument structure, stance target, and polarization markers for analyzing Indonesian political talk at scale.

Page 2 of 2 | Total Record : 18