Publications

@inproceedings{zaghouani-etal-2025-mahedb,

title = {MAHED Shared Task: Multimodal Detection of Hope and Hate Emotions in Arabic Content},

author = {Wajdi Zaghouani and Md. Rafiul Biswas and Mabrouka Bessghaier and Shimaa Ibrahim and George Mikros and Abul Hasnat and Firoj Alam},

editor = {Kareem Darwish and Ahmed Ali and Ibrahim Abu Farha and Samia Touileb and Imed Zitouni and Ahmed Abdelali and Sharefah Al-Ghamdi and Sakhar Alkhereyf and Wajdi Zaghouani and Salam Khalifa and Badr AlKhamissi and Rawan Almatham and Injy Hamed and Zaid Alyafeai and Areeb Alowisheq and Go Inoue and Khalil Mrini and Waad Alshammari},

url = {https://aclanthology.org/2025.arabicnlp-sharedtasks.75/},

doi = {10.18653/v1/2025.arabicnlp-sharedtasks.75},

isbn = {979-8-89176-356-2},

year  = {2025},

date = {2025-11-01},

urldate = {2025-11-01},

booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},

pages = {560–574},

publisher = {Association for Computational Linguistics},

address = {Suzhou, China},

abstract = {This paper presents the MAHED 2025 Shared Task on Multimodal Detection of Hope and Hate Emotions in Arabic Content, comprising three subtasks: (1) text-based classification of Arabic content into hate and hope, (2) multi-task learning for joint prediction of emotions, offensive content, and hate speech, and (3) multimodal detection of hateful content in Arabic memes. We provide three high-quality datasets totaling over 22,000 instances sourced from social media platforms, annotated by native Arabic speakers with Cohen's Kappa exceeding 0.85. Our evaluation attracted 46 leaderboard submissions from participants, with systems leveraging Arabic-specific pre-trained language models (AraBERT, MARBERT), large language models (GPT-4, Gemini), and multimodal fusion architectures combining CLIP vision encoders with Arabic text models. The best-performing systems achieved macro F1-scores of 0.723 (Task 1), 0.578 (Task 2), and 0.796 (Task 3), with top teams employing ensemble methods, class-weighted training, and OCR-aware multimodal fusion. Analysis reveals persistent challenges in dialectal robustness, minority class detection for hope speech, and highlights key directions for future Arabic content moderation research.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hasanain-etal-2025-propxplain,

title = {PropXplain: Can LLMs Enable Explainable Propaganda Detection?},

author = {Maram Hasanain and Md Arid Hasan and Mohamed Bayan Kmainasi and Elisa Sartori and Ali Ezzat Shahroor and Giovanni Da San Martino and Firoj Alam},

editor = {Christos Christodoulopoulos and Tanmoy Chakraborty and Carolyn Rose and Violet Peng},

url = {https://aclanthology.org/2025.findings-emnlp.1296/},

doi = {10.18653/v1/2025.findings-emnlp.1296},

isbn = {979-8-89176-335-7},

year  = {2025},

date = {2025-11-01},

urldate = {2025-11-01},

booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025},

pages = {23855–23863},

publisher = {Association for Computational Linguistics},

address = {Suzhou, China},

abstract = {There has been significant research on propagandistic content detection across different modalities and languages. However, most studies have primarily focused on detection, with little attention given to explanations justifying the predicted label. This is largely due to the lack of resources that provide explanations alongside annotated labels. To address this issue, we propose a multilingual (i.e., Arabic and English) explanation-enhanced dataset, the first of its kind. Additionally, we introduce an explanation-enhanced LLM for both label detection and rationale-based explanation generation. Our findings indicate that the model performs comparably while also generating explanations. We will make the dataset and experimental resources publicly available for the research community (https://github.com/firojalam/PropXplain).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bassi-etal-2025-annotating,

title = {Annotating the Annotators: Analysis, Insights and Modelling from an Annotation Campaign on Persuasion Techniques Detection},

author = {Davide Bassi and Dimitar Iliyanov Dimitrov and Bernardo D'Auria and Firoj Alam and Maram Hasanain and Christian Moro and Luisa Orrù and Gian Piero Turchi and Preslav Nakov and Giovanni Da San Martino},

editor = {Wanxiang Che and Joyce Nabende and Ekaterina Shutova and Mohammad Taher Pilehvar},

url = {https://aclanthology.org/2025.findings-acl.922/},

doi = {10.18653/v1/2025.findings-acl.922},

isbn = {979-8-89176-256-5},

year  = {2025},

date = {2025-07-01},

urldate = {2025-07-01},

booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},

pages = {17918–17929},

publisher = {Association for Computational Linguistics},

address = {Vienna, Austria},

abstract = {Persuasion (or propaganda) techniques detection is a relatively novel task in Natural Language Processing (NLP). While there have already been a number of annotation campaigns, they have been based on heuristic guidelines, which have never been thoroughly discussed. Here, we present the first systematic analysis of a complex annotation task -detecting 22 persuasion techniques in memes-, for which we provided continuous expert oversight. The presence of an expert allowed us to critically analyze specific aspects of the annotation process. Among our findings, we show that inter-annotator agreement alone inadequately assessed annotation correctness. We thus define and track different error types, revealing that expert feedback shows varying effectiveness across error categories. This pattern suggests that distinct mechanisms underlie different kinds of misannotations. Based on our findings, we advocate for an expert oversight in annotation tasks and periodic quality audits. As an attempt to reduce the costs for this, we introduce a probabilistic model for optimizing intervention scheduling.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kmainasi-etal-2025-llamalens,

title = {LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content},

author = {Mohamed Bayan Kmainasi and Ali Ezzat Shahroor and Maram Hasanain and Sahinur Rahman Laskar and Naeemul Hassan and Firoj Alam},

editor = {Luis Chiruzzo and Alan Ritter and Lu Wang},

url = {https://aclanthology.org/2025.findings-naacl.313/},

doi = {10.18653/v1/2025.findings-naacl.313},

isbn = {979-8-89176-195-7},

year  = {2025},

date = {2025-04-01},

urldate = {2025-04-01},

booktitle = {Findings of the Association for Computational Linguistics: NAACL 2025},

pages = {5642–5664},

publisher = {Association for Computational Linguistics},

address = {Albuquerque, New Mexico},

abstract = {Large Language Models (LLMs) have demonstrated remarkable success as general-purpose task solvers across various fields. However, their capabilities remain limited when addressing domain-specific problems, particularly in downstream NLP tasks. Research has shown that models fine-tuned on instruction-based downstream NLP datasets outperform those that are not fine-tuned. While most efforts in this area have primarily focused on resource-rich languages like English and broad domains, little attention has been given to multilingual settings and specific domains. To address this gap, this study focuses on developing a specialized LLM, LlamaLens, for analyzing news and social media content in a multilingual context. To the best of our knowledge, this is the first attempt to tackle both domain specificity and multilinguality, with a particular focus on news and social media. Our experimental setup includes 18 tasks, represented by 52 datasets covering Arabic, English, and Hindi. We demonstrate that LlamaLens outperforms the current state-of-the-art (SOTA) on 23 testing sets, and achieves comparable performance on 8 sets. We make the models and resources publicly available for the research community (https://huggingface.co/QCRI).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1007/978-3-031-88720-8_68,

title = {The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval},

author = {Firoj Alam and Julia Maria Struß and Tanmoy Chakraborty and Stefan Dietze and Salim Hafid and Katerina Korre and Arianna Muti and Preslav Nakov and Federico Ruggeri and Sebastian Schellhammer and Vinay Setty and Megha Sundriyal and Konstantin Todorov and Venktesh V.},

editor = {Claudia Hauff and Craig Macdonald and Dietmar Jannach and Gabriella Kazai and Franco Maria Nardini and Fabio Pinelli and Fabrizio Silvestri and Nicola Tonellotto},

isbn = {978-3-031-88720-8},

year  = {2025},

date = {2025-01-01},

booktitle = {Advances in Information Retrieval},

pages = {467–478},

publisher = {Springer Nature Switzerland},

address = {Cham},

abstract = {The CheckThat! lab aims to advance the development of innovative technologies designed to identify and to counteract online disinformation and manipulation efforts across various languages and platforms. The first five editions of the CheckThat! lab focused on the main tasks of the information verification pipeline: check-worthiness, evidence retrieval and pairing, and verification. Since the 2023 edition, the lab has broadened the focus and addressed new problems on auxiliary tasks supporting research and decision-making during the verification process. In the 2025 edition of the lab, we consider tasks at the core of the verification pipeline again as well as auxiliary tasks: Task 1 is on identification of subjectivity (a follow up of the CheckThat! 2024 edition), Task 2 is on claim normalization, Task 3 addresses fact-checking numerical claims, and Task 4 focuses on scientific web discourse processing. These tasks represent challenging classification and retrieval problems at the document and at the span level, including multilingual settings.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sartori2025insights,

title = {Insights into using temporal coordinated behaviour to explore connections between social media posts and influence},

author = {Elisa Sartori and Serena Tardelli and Maurizio Tesconi and Mauro Conti and Alessandro Galeazzi and Stefano Cresci and Giovanni Da San Martino and others},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025},

pages = {24392–24404},

organization = {Association for Computational Linguistics},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{noman2025user,

title = {User Correction of Misinformation on Social Media: Exploring Communication Styles and the Influence of Empathy, Altruism, Self-esteem, and Competency},

author = {Muaadh Noman and Firoj Alam and Raian Ali},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

booktitle = {Conference on e-Business, e-Services and e-Society},

pages = {409–422},

organization = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{alam2025clef,

title = {The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval},

author = {Firoj Alam and Julia Maria Struß and Tanmoy Chakraborty and Stefan Dietze and Salim Hafid and Katerina Korre and Arianna Muti and Preslav Nakov and Federico Ruggeri and Sebastian Schellhammer and others},

url = {https://arxiv.org/abs/2503.14828},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

booktitle = {European Conference on Information Retrieval},

pages = {467–478},

organization = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{alam-etal-2024-armeme,

title = {ÄrMeme: Propagandistic Content in Arabic Memes"},

author = {Firoj Alam and Abul Hasnat and Fatema Ahmad and Md. Arid Hasan and Maram Hasanain},

editor = {Yaser Al-Onaizan and Mohit Bansal and Yun-Nung Chen},

url = {https://aclanthology.org/2024.emnlp-main.1173},

year  = {2024},

date = {2024-11-01},

booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},

pages = {21071–21090},

publisher = {Association for Computational Linguistics},

address = {Miami, Florida, USA},

abstract = {With the rise of digital communication memes have become a significant medium for cultural and political expression that is often used to mislead audience. Identification of such misleading and persuasive multimodal content become more important among various stakeholders, including social media platforms, policymakers, and the broader society as they often cause harm to the individuals, organizations and/or society. While there has been effort to develop AI based automatic system for resource rich languages (e.g., English), it is relatively little to none for medium to low resource languages. In this study, we focused on developing an Arabic memes dataset with manual annotations of propagandistic content. We annotated $sim6K$ Arabic memes collected from various social media platforms, which is a first resource for Arabic multimodal research. We provide a comprehensive analysis aiming to develop computational tools for their detection. We made the dataset publicly available for the community.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hasanain-etal-2024-large,

title = {Large Language Models for Propaganda Span Annotation},

author = {Maram Hasanain and Fatema Ahmad and Firoj Alam},

editor = {Yaser Al-Onaizan and Mohit Bansal and Yun-Nung Chen},

url = {https://aclanthology.org/2024.findings-emnlp.850},

year  = {2024},

date = {2024-11-01},

urldate = {2024-11-01},

booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},

pages = {14522–14532},

publisher = {Association for Computational Linguistics},

address = {Miami, Florida, USA},

abstract = {The use of propagandistic techniques in online content has increased in recent years aiming to manipulate online audiences. Fine-grained propaganda detection and extraction of textual spans where propaganda techniques are used, are essential for more informed content consumption. Automatic systems targeting the task over lower resourced languages are limited, usually obstructed by lack of large scale training datasets. Our study investigates whether Large Language Models (LLMs), such as GPT-4, can effectively extract propagandistic spans. We further study the potential of employing the model to collect more cost-effective annotations. Finally, we examine the effectiveness of labels provided by GPT-4 in training smaller language models for the task. The experiments are performed over a large-scale in-house manually annotated dataset. The results suggest that providing more annotation context to GPT-4 within prompts improves its performance compared to human annotators. Moreover, when serving as an expert annotator (consolidator), the model provides labels that have higher agreement with expert annotators, and lead to specialized models that achieve state-of-the-art over an unseen Arabic testing set. Finally, our work is the first to show the potential of utilizing LLMs to develop annotated datasets for propagandistic spans detection task prompting it with annotations from human annotators with limited expertise. All scripts and annotations will be shared with the community.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}