🧑‍🔬 Simon Dobnik

🏛️ Affiliations

🎓University of GothenburgGothenburg · Sweden2012–2026 · 46 papersEmployment since 2020 · Professor of Computational Linguistics, Department of Philosophy, Linguistics and Theory of Sciencecurrent🎓University of OxfordOxford · United Kingdom2002–2010 · 3 papersEducation until 2010🔬Språkbanken TextGothenburg2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Shami: A Corpus of Levantine Arabic Dialects (2018 · 95 citations)
   Arabic NLP tools are built mostly for Modern Standard Arabic (MSA), but everyday online writing uses regional dialects that differ from MSA in vocabulary and usage.
2. An Arabic Tweets Sentiment Analysis Dataset (ATSAD) using Distant Supervision and Self Training (2020 · 38 citations)
   Arabic sentiment analysis lacks social-media resources that are both large and reliably labelled. Existing corpora are often small, limited to one dialect, unbalanced, or labelled in ways that distort the original text. The authors build ATSAD, a Twitter corpus of 36K Arabic tweets marked as positive or negative.…
3. Identification of Languages in Algerian Arabic Multilingual Documents (2017 · 35 citations)
   Social media posts by Algerian Arabic speakers often switch between several languages within one text, while most NLP tools assume a document is in a single language.
4. Can Modern Standard Arabic Approaches be used for Arabic Dialects? Sentiment Analysis as a Case Study (2019 · 6 citations)
   The paper asks whether sentiment classifiers built for Modern Standard Arabic (MSA) still work on dialectal Arabic (DA), or whether each dialect needs its own models.
5. Pre-trained Models or Feature Engineering: The Case of Dialectal Arabic (2022 · 2 citations)
   Published work on Arabic dialects reports results on corpora that differ in size, dialect coverage and quality, so it is hard to say whether neural models really beat classic classifiers on Dialectal Arabic.
6. Birds of a Feather: Do Embedding Representations of Personal Information Flock Together? (2026)
   Automatic de-identification usually relies on embedding representations to find and classify personal information (PI).

All works

9 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. Shami: A Corpus of Levantine Arabic DialectsLanguage Resources and Evaluation Conference (LREC)Kathrein Abu Kwaik, Motaz Saad, Stergios Chatzikyriakidis, et al.2018 · 95 citations
2. An Arabic Tweets Sentiment Analysis Dataset (ATSAD) using Distant Supervision and Self TrainingWorkshop on Open-Source Arabic Corpora and Processing Tools with Shared TasksKathrein Abu Kwaik, Stergios Chatzikyriakidis, Simon Dobnik, et al.2020 · 38 citations
3. Identification of Languages in Algerian Arabic Multilingual DocumentsArabic Natural Language Processing Workshop (WANLP)Wafia Adouane, Simon Dobnik2017 · 35 citations
4. Can Modern Standard Arabic Approaches be used for Arabic Dialects? Sentiment Analysis as a Case StudyWorkshop on Arabic Corpus LinguisticsKathrein Abu Kwaik, Stergios Chatzikyriakidis, Simon Dobnik2019 · 6 citations
5. Did the Names I Used within My Essay Affect My Score? Diagnosing Name Biases in Automated Essay Scoring ↗Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024) · no summary yetRicardo Muñoz Sánchez et al.2024 · 3 citations
6. Detecting Personal Identifiable Information in Swedish Learner Essays ↗Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024) · no summary yetMaria Irena Szawerna et al.2024 · 3 citations
7. The Devil's in the Details: the Detailedness of Classes Influences Personal Information Detection and Labeling ↗Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025) · no summary yetMaria Irena Szawerna et al.2025 · 2 citations
8. Pre-trained Models or Feature Engineering: The Case of Dialectal ArabicWorkshop on Open-Source Arabic Corpora and Processing Tools with Shared TasksKathrein Abu Kwaik, Stergios Chatzikyriakidis, Simon Dobnik2022 · 2 citations
9. Birds of a Feather: Do Embedding Representations of Personal Information Flock Together?Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Computational Approaches to Language Data Pseudonymization, Anonymization, De-identification, and Data Privacy @ LRECMaria Irena Szawerna, Simon Dobnik2026

🤝 Co-authors here

6 co-authors with a page, the most papers together first.

• Kathrein Abu Kwaik ×4
• Stergios Chatzikyriakidis ×4
• Motaz Saad ×2
• Maria Irena Szawerna
• Richard Johansson
• Wafia Adouane

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks ×2: Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks 2022, Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks 2020
• Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024) ×2
• Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Computational Approaches to Language Data Pseudonymization, Anonymization, De-identification, and Data Privacy @ LREC: Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Computational Approaches to Language Data Pseudonymization, Anonymization, De-identification, and Data Privacy @ LREC 2026
• Language Resources and Evaluation Conference (LREC): LREC 2018
• Workshop on Arabic Corpus Linguistics: Workshop on Arabic Corpus Linguistics 2019
• Arabic Natural Language Processing Workshop (WANLP): WANLP 2017
• Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)

🔗 Cited by

Papers of our library cite their works 71 times (of the 149,439 papers whose bibliographies we read); 45 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/simon-dobnik/