Conference
2026
Accepted
Translation-Induced Label Drift in Natural Language Inference: Evidence from Nine Languages
Muhammad S. Abdo, Jose Benavides, Phakphum Artkaew, Elias Naske, Wenchen Shi, Hale Karkoutli, Elder Henrique Attala e Paiva, Sadia Ashraf, Jinyuan Wang, Melissa Lieffers, Sandra Kübler
Accepted to the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026).
Evidence from nine languages showing how translation can shift natural language inference labels and affect the reliability of multilingual evaluation.
BibTeX citation
@inproceedings{abdo2026translation,
title={Translation-Induced Label Drift in Natural Language Inference: Evidence from Nine Languages},
author={Muhammad S. Abdo and Jose Benavides and Phakphum Artkaew and Elias Naske and Wenchen Shi and Hale Karkoutli and Elder Henrique Attala e Paiva and Sadia Ashraf and Jinyuan Wang and Melissa Lieffers and Sandra K{\"u}bler},
booktitle={EMNLP 2026 Main Conference},
year={2026},
url={https://openreview.net/forum?id=RDafhrNnbK}
}
Book Chapter
2026
Forthcoming
Diminutives in North African Varieties of Arabic
Stuart Davis, Muhammad S. Abdo
To appear in The Handbook of North African Arabic. Book chapter, August 2026.
A forthcoming chapter on diminutive formation and usage in North African varieties of Arabic, with attention to morphological patterns, dialectal variation, and the linguistic functions of diminutives across the region.
Roundtable
2026
Newsletter
Roundtable Discussion: AI in MENA Politics Research
Carolyn Barnett, Muhammad S. Abdo, Tariq Adely, Cinzia Bianco, Ashrakat Elshehawy, Robert Kubinec, Michael Robbins
APSA MENA Newsletter, 9(1):55–73. American Political Science Association (APSA) MENA Section.
A roundtable discussion on how artificial intelligence is reshaping MENA politics research, with attention to regional data, methodological challenges, governance concerns, and the role of domain expertise in evaluating AI systems.
Journal
2025
Ellipsis in Arabic: Using Machine Learning to Detect and Predict Elided Words
Muhammad S. Abdo, Damir Cavar, Billy Dickson, Attia Youseif
Arabic Linguistics, 1(2):240–263. John Benjamins.
The study introduced the first comprehensive Arabic dataset for tracking missing words (ellipsis). Testing showed that while LLMs easily detect if a sentence has missing words, they severely struggle to locate and reconstruct those missing words.
Journal
2025
★ 1 cite
Allocution, Sentencing, and Viewers' Comments in YouTube-mediated Trials of Convicted Young Murderers: An Appraisal-Sentiment Analysis
Aisha A. El Attar, Muhammad S. Abdo
Language and Semiotic Studies, 11(4):636–660.
Summary: This study combines appraisal theory and sentiment analysis to compare how judges, perpetrators, and YouTube viewers evaluate morality in high-profile courtroom discourse. It treats the audience as a third discursive actor and shows how public reaction extends the meaning-making of the trial beyond the courtroom.
Workshop
2025
★ 1 cite
AMWAL: Named Entity Recognition for Arabic Financial News
Muhammad S. Abdo, Yash Hatekar, Damir Cavar
Proceedings of the Joint Workshop FinNLP, FNP & LLMFinLegal @ COLING 2025, Abu Dhabi.
Summary: AMWAL introduces the first domain-specific Arabic financial NER system, trained on 26K news articles and grounded in the FIBO ontology. It recognizes 20 entity types and reaches a 95.97 F1 score, outperforming CamelBERT and Wojood.
Journal
2024
★ 1 cite
Thus Spoke a Couple: A Corpus-Based Content Analysis of Spousal Duties Fatwas
Muhammad S. Abdo, Abdullah Omran, Said F. Hassan
Journal of Digital Islamicate Research, 1(1-2):37–65.
Summary: Using a 150,000-fatwa corpus from Islamweb.net, this study shifts attention from muftis to the spouses who ask the questions. It maps the lived concerns behind marital conflict and shows how online fatwa requests reveal recurring themes in spousal duties.
Conference
2024
★ 14 cites
The Typology of Ellipsis: A Corpus for Linguistic Analysis and Machine Learning Applications
Damir Cavar, Louis V. Mompelat, Muhammad S. Abdo
Proceedings of the 6th Workshop on Research in Computational Linguistic Typology (SIGTYP 2024) @ EACL.
Summary: This paper introduces a multilingual corpus of ellipsis annotated for linguistic analysis and machine-learning experiments. It connects cross-linguistic variation in omitted material with reusable data and computational prediction tasks.
Conference
2023
★ 3 cites
IUNADI at NADI 2023 Shared Task: Country-level Arabic Dialect Classification in Tweets
Yash Hatekar, Muhammad S. Abdo
Proceedings of ArabicNLP 2023, 665–669.
Summary: This paper presents the IUNADI system for the NADI 2023 shared task on country-level Arabic dialect identification in tweets. It addresses fine-grained dialect variation across Arabic-speaking regions by framing the problem as tweet-level classification and evaluating a competitive approach for robust dialect prediction in noisy social-media text.
Conference
2023
★ 3 cites
IUEXIST: Multilingual Pre-trained Language Models for Sexism Detection on Twitter in EXIST2023
Yash Hatekar, Muhammad S. Abdo, Sidharth Khanna, Sandra Kübler
CLEF 2023 Working Notes, 950–958.
Summary: IUEXIST applies multilingual transformer models to sexism detection on English and Spanish tweets in the EXIST shared task. The system compares a single XLM-R Large model against an ensemble with extended training data, showing that the ensemble improves hard cases while the single model remains stronger on softer labels.
Journal
2020
★ 76 cites
How Do Arab Tweeters Perceive the COVID-19 Pandemic?
Basma A. Essam, Muhammad S. Abdo
Journal of Psycholinguistic Research (2020).
Summary: This study analyzes Arabic tweets about COVID-19 using thematic coding, LIWC-based psycholinguistic profiling with a custom Arabic dictionary, and temporal discourse analysis to trace how public framing evolved during the early pandemic period.
Journal
2020
★ 22 cites
Public Perception of COVID-19's Global Health Crisis on Twitter until 14 Weeks after the Outbreak
Muhammad S. Abdo, Abdulrahman S. Alghonaim, Basma A. Essam
Digital Scholarship in the Humanities (2020).
Summary: Based on 992,593 English tweets from the first 14 weeks of the outbreak, this paper combines corpus linguistics, LIWC analysis, and conceptual metaphor analysis to show sustained analytical reasoning alongside persistently negative tone and shifting emotional patterns.
Journal
2019
★ 5 cites
Analyzing Judgment in Bipolar Depression Patients' Narratives Using Syntactic Patterns: A Corpus-Based Study
Muhammad S. Abdo, Aya Y. Ali, Nourhan N. Sarhan
The Egyptian Journal of Language Engineering, 6(1):1–11.
Summary: This corpus-based study examines how people with bipolar depression express judgment through recurring syntactic patterns in personal narratives, linking grammatical choices to appraisal and mental-health discourse.
MA Thesis
2021
Analyzing Appraisal in Major and Bipolar Depression Patients' Narratives in Mental Health Forums: A Corpus-Based Study
Muhammad S. Abdo
MA Thesis, Ain Shams University (Al-Alsun). Advisor: Dr. Nihal Nagi Sarhan. Unpublished.
Summary: This thesis compares appraisal patterns in narratives by people describing major and bipolar depression. It uses corpus evidence from mental-health forums to study how evaluation, affect, and judgment are expressed across the two groups.