Online social media platforms have become central to communication and information exchange, however, they also serve as fertile ground for hate speech, offensive language, and bullying targeting individuals and communities.Such content undermines online safety and inclusion, underscoring the need for reliable detection systems-especially in lowresource languages with limited moderation tools.For Bangla, existing work provides valuable resources and models, however, they are mostly single-task (e.g., binary hate/offense) with narrow coverage of key dimensions such as type, severity, and target.We address these gaps by introducing the first multi-task Bangla hate-speech dataset, BanglaMultiHate, one of the largest manually annotated dataset to date.Using this resource, we performed a comparative study across different baselines, monolingual pretrained models, and LLMs under zeroshot, few-shot, and LoRA fine-tuning settings.Our findings show that while LoRA-tuned LLMs rival BanglaBERT, culturally grounded pretraining remains crucial for robust performance.Overall, BanglaMultiHate establishes a stronger benchmark for hate speech detection in low-resource contexts.All data 1 and scripts 2 are released for reproducibility.

Arabic, with its rich diversity of dialects, remains significantly underrepresented in Large Language Models, particularly in dialectal variations. We address this gap by introducing seven synthetic datasets in dialects alongside Modern Standard Arabic (MSA), created using Machine Translation (MT) combined with human post-editing. We present AraDiCE, a benchmark for Arabic Dialect and Cultural Evaluation. We evaluate LLMs on dialect comprehension and generation, focusing specifically on low-resource Arabic dialects. Additionally, we introduce the first-ever fine-grained benchmark designed to evaluate cultural awareness across the Gulf, Egypt, and Levant regions, providing a novel dimension to LLM evaluation. Our findings demonstrate that while Arabic-specific models like Jais and AceGPT outperform multilingual models on dialectal tasks, significant challenges persist in dialect identification, generation, and translation. This work contributes ≈45K post-edited samples, a cultural benchmark, and highlights the importance of tailored training to improve LLM performance in capturing the nuances of diverse Arabic dialects and cultural contexts. We have released the dialectal translation models and benchmarks developed in this study (https://huggingface.co/datasets/QCRI/AraDiCE)

The proliferation of multimodal content on social media presents significant challenges in understanding and moderating complex, contextdependent issues such as misinformation, hate speech, and propaganda.While efforts have been made to develop resources and propose new methods for automatic detection, limited attention has been given to jointly modeling label detection and the generation of explanationbased rationales, which often leads to degraded classification performance when trained simultaneously.To address this challenge, we introduce MemeXplain, an explanation-enhanced dataset for propagandistic memes in Arabic and hateful memes in English, making it the first large-scale resource for these tasks.To solve these tasks, we propose a multistage optimization approach and train Vision-Language Models (VLMs).Our results show that this strategy significantly improves both label detection and explanation generation quality over the base model, outperforming the current state-of-the-art with an absolute improvement of ∼ 1.4% (Acc) on ArMeme and ∼ 2.2% (Acc) on Hateful Memes.For reproducibility and future research, we aim to make the MemeXplain dataset and scripts publicly available.1

In this study, we present the first large dataset, ThatiAR, for subjectivity detection in Arabic, consisting of ~3.6K manually annotated sentences, and GPT-4o based explanations. In addition, we include instructions (both in English and Arabic) to facilitate LLM based fine-tuning. We provide an in-depth analysis of the dataset, annotation process, and extensive benchmark results, including PLMs and LLMs. Our analysis of the annotation process highlights that annotators were strongly influenced by their political, cultural, and religious backgrounds, especially at the beginning of the annotation process. The experimental results suggest that LLMs with in-context learning provide better performance. We release the dataset and resources to the community.

The rapid expansion of the digital world has propelled sentiment analysis into a critical tool across diverse sectors such as marketing, politics, customer service, and healthcare. While there have been significant advancements in sentiment analysis for widely spoken languages, low-resource languages, such as Bangla, remain largely under-researched due to resource constraints. Furthermore, the recent unprecedented performance of Large Language Models (LLMs) in various applications highlights the need to evaluate them in the context of low-resource languages. In this study, we present a sizeable manually annotated dataset encompassing 33,606 Bangla news tweets and Facebook comments. We also investigate zero- and few-shot in-context learning with several language models, including Flan-T5, GPT-4, and Bloomz, offering a comparative analysis against fine-tuned models. Our findings suggest that monolingual transformer-based models consistently outperform other models, even in zero and few-shot scenarios. To foster continued exploration, we intend to make this dataset and our research tools publicly available to the broader research community.

The use of propaganda has spiked on mainstream and social media, aiming to manipulate or mislead users. While efforts to automatically detect propaganda techniques in textual, visual, or multimodal content have increased, most of them primarily focus on English content. The majority of the recent initiatives targeting medium to low-resource languages produced relatively small annotated datasets, with a skewed distribution, posing challenges for the development of sophisticated propaganda detection models. To address this challenge, we carefully develop the largest propaganda dataset to date, ArPro, comprised of 8K paragraphs from newspaper articles, labeled at the text span level following a taxonomy of 23 propagandistic techniques. Furthermore, our work offers the first attempt to understand the performance of large language models (LLMs), using GPT-4, for fine-grained propaganda detection from text. Results showed that GPT-4’s performance degrades as the task moves from simply classifying a paragraph as propagandistic or not, to the fine-grained task of detecting propaganda techniques and their manifestation in text. Compared to models fine-tuned on the dataset for propaganda detection at different classification granularities, GPT-4 is still far behind. Finally, we evaluate GPT-4 on a dataset consisting of six other languages for span detection, and results suggest that the model struggles with the task across languages. We made the dataset publicly available for the community.

Ahmed Abdelali, Hamdy Mubarak, Shammur Chowdhury, Maram Hasanain, Basel Mousi, Sabri Boughorbel, Samir Abdaljalil, Yassine El Kheir, Daniel Izham, Fahim Dalvi, Majd Hawasly, Nizi Nazar, Youssef Elshahawy, Ahmed Ali, Nadir Durrani, Natasa Milic-Frayling, Firoj Alam. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

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. 1 We annotated ∼ 6K 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.

Images shared on social media help crisis managers gain situational awareness and assess incurred damages, among other response tasks. As the volume and velocity of such content are typically high, real-time image classification has become an urgent need for faster disaster response. Recent advances in computer vision and deep neural networks have enabled the development of models for image classification for a number of tasks, including detecting crisis incidents, filtering irrelevant images, classifying images into specific humanitarian categories, and assessing the severity of the damage. To develop robust models, it is necessary to understand the capability of the publicly available pretrained models for these tasks, which remains to be underexplored in the crisis informatics literature. In this study, we address such limitations by investigating ten different network architectures for four different tasks using the largest publicly available datasets for these tasks. We also explore various data augmentation strategies, semisupervised techniques, and a multitask learning setup. In our extensive experiments, we achieve promising results.

The opacity of deep neural networks remains a challenge in deploying solutions where explanation is as important as precision. We present ConceptX, a human-in-the-loop framework for interpreting and annotating latent representational space in pre-trained Language Models (pLMs). We use an unsupervised method to discover concepts learned in these models and enable a graphical interface for humans to generate explanations for the concepts. To facilitate the process, we provide auto-annotations of the concepts (based on traditional linguistic ontologies). Such annotations enable development of a linguistic resource that directly represents latent concepts learned within deep NLP models. These include not just traditional linguistic concepts, but also task-specific or sensitive concepts (words grouped based on gender or religious connotation) that helps the annotators to mark bias in the model. The framework consists of two parts (i) concept discovery and (ii) annotation platform.

Abstract Recent research in disaster informatics demonstrates a practical and important use case of artificial intelligence to save human lives and suffering during natural disasters based on social media contents (text and images). While notable progress has been made using texts, research on exploiting the images remains relatively under-explored. To advance image-based approaches, we propose MEDIC ( https://crisisnlp.qcri.org/medic/index.html ), which is the largest social media image classification dataset for humanitarian response consisting of 71,198 images to address four different tasks in a multi-task learning setup. This is the first dataset of its kind: social media images, disaster response, and multi-task learning research. An important property of this dataset is its high potential to facilitate research on multi-task learning , which recently receives much interest from the machine learning community and has shown remarkable results in terms of memory, inference speed, performance, and generalization capability. Therefore, the proposed dataset is an important resource for advancing image-based disaster management and multi-task machine learning research. We experiment with different deep learning architectures and report promising results, which are above the majority baselines for all tasks. Along with the dataset, we also release all relevant scripts ( https://github.com/firojalam/medic ).

The growing use of media has led to the development of several machine learning (ML) and natural language processing (NLP) tools to process the unprecedented amount of social media content to make actionable decisions. However, these ML and NLP algorithms have been widely shown to be vulnerable to adversarial attacks. These vulnerabilities allow adversaries to launch a diversified set of adversarial attacks on these algorithms in different applications of social media text processing. In this article, we provide a comprehensive review of the main approaches for adversarial attacks and defenses in the context of social media applications with a particular focus on key challenges and future research directions. In detail, we cover literature on six key applications: 1) rumors detection; 2) satires detection; 3) clickbaits and spams identification; 4) hate speech detection; 5) misinformation detection; and 6) sentiment analysis. We then highlight the concurrent and anticipated future research questions and provide recommendations and directions for future work.

Formal response organizations perform rapid damage assessments after natural and human-induced disasters to measure the extent of damage to infrastructures such as roads, bridges, and buildings. This time-critical task, when performed using traditional approaches such as experts surveying the disaster areas, poses serious challenges and delays response. This paper presents an AI-based system that leverages citizen science to collect damage images reported on social media and perform rapid damage assessment in real-time. Several image processing models in the system tackle non-trivial challenges posed by social media as a data source, such as high-volume of redundant and irrelevant content. The system determines the severity of damage using a state-of-the-art computer vision model. Together with a response organization in the US, we deployed the system to identify damage reports during a major real-world disaster. We observe that almost 42% of the images are unique, 28% relevant, and more importantly, only 10% of them contain either mild or severe damage. Experts from our partner organization provided feedback on the system's mistakes, which we used to perform additional experiments to retrain the models. Consequently, the retrained models based on expert feedback on the target domain data helped us achieve significant performance improvements.

Recent years have witnessed the proliferation of offensive content online such as fake news, propaganda, misinformation, and disinformation. While initially this was mostly about textual content, over time images and videos gained popularity, as they are much easier to consume, attract more attention, and spread further than text. As a result, researchers started leveraging different modalities and combinations thereof to tackle online multimodal offensive content. In this study, we offer a survey on the state-of-the-art on multimodal disinformation detection covering various combinations of modalities: text, images, speech, video, social media network structure, and temporal information. Moreover, while some studies focused on factuality, others investigated how harmful the content is. While these two components in the definition of disinformation – (i) factuality, and (ii) harmfulness –, are equally important, they are typically studied in isolation. Thus, we argue for the need to tackle disinformation detection by taking into account multiple modalities as well as both factuality and harmfulness, in the same framework. Finally, we discuss current challenges and future research directions.

Post-processing of static embedding has been shown to improve their performance on both lexical and sequence-level tasks. However, post-processing for contextualized embeddings is an under-studied problem. In this work, we question the usefulness of post-processing for contextualized embeddings obtained from different layers of pre-trained language models. More specifically, we standardize individual neuron activations using z-score, min-max normalization, and by removing top principal components using the all-but-the-top method. Additionally, we apply unit length normalization to word representations. On a diverse set of pre-trained models, we show that post-processing unwraps vital information present in the representations for both lexical tasks (such as word similarity and analogy) and sequence classification tasks. Our findings raise interesting points in relation to the research studies that use contextualized representations, and suggest z-score normalization as an essential step to consider when using them in an application.

We study the evolution of latent space in finetuned NLP models.Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations.More specifically, we discover latent concepts in the representational space using hierarchical clustering.We then use an alignment function to gauge the similarity between the latent space of a pre-trained model and its finetuned version.We use traditional linguistic concepts to facilitate our understanding and also study how the model space transforms towards task-specific information.We perform a thorough analysis, comparing pre-trained and finetuned models across three models and three downstream tasks.The notable findings of our work are: i) the latent space of the higher layers evolve towards task-specific concepts, ii) whereas the lower layers retain generic concepts acquired in the pre-trained model, iii) we discovered that some concepts in the higher layers acquire polarity towards the output class, and iv) that these concepts can be used for generating adversarial triggers.

The automatic identification of harmful content online is of major concern for social media platforms, policymakers, and society. Researchers have studied textual, visual, and audio content, but typically in isolation. Yet, harmful content often combines multiple modalities, as in the case of memes. With this in mind, here we offer a comprehensive survey with a focus on harmful memes. Based on a systematic analysis of recent literature, we first propose a new typology of harmful memes, and then we highlight and summarize the relevant state of the art. One interesting finding is that many types of harmful memes are not really studied, e.g., such featuring self-harm and extremism, partly due to the lack of suitable datasets. We further find that existing datasets mostly capture multi-class scenarios, which are not inclusive of the affective spectrum that memes can represent. Another observation is that memes can propagate globally through repackaging in different languages and that they can also be multilingual, blending different cultures. We conclude by highlighting several challenges related to multimodal semiotics, technological constraints, and non-trivial social engagement, and we present several open-ended aspects such as delineating online harm and empirically examining related frameworks and assistive interventions, which we believe will motivate and drive future research.

The emergence of the COVID-19 pandemic and the first global infodemic have changed our lives in many different ways. We relied on social media to get the latest information about COVID-19 pandemic and at the same time to disseminate information. The content in social media consisted not only health related advice, plans, and informative news from policymakers, but also contains conspiracies and rumors. It became important to identify such information as soon as they are posted to make an actionable decision (e.g., debunking rumors, or taking certain measures for traveling). To address this challenge, we develop and publicly release the first largest manually annotated Arabic tweet dataset, ArCovidVac, for COVID-19 vaccination campaign, covering many countries in the Arab region. The dataset is enriched with different layers of annotation, including, (i) Informativeness more vs. less importance of the tweets); (ii) fine-grained tweet content types (e.g., advice, rumors, restriction, authenticate news/information); and (iii) stance towards vaccination (pro-vaccination, neutral, anti-vaccination). Further, we performed in-depth analysis of the data, exploring the popularity of different vaccines, trending hashtags, topics, and presence of offensiveness in the tweets. We studied the data for individual types of tweets and temporal changes in stance towards vaccine. We benchmarked the ArCovidVac dataset using transformer architectures for informativeness, content types, and stance detection.

Hassan Sajjad, Nadir Durrani, Fahim Dalvi, Firoj Alam, Abdul Khan, Jia Xu. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Social media have democratized content creation and have made it easy for anybody to spread information online. However, stripping traditional media from their gate-keeping role has left the public unprotected against biased, deceptive and disinformative content, which could now travel online at breaking-news speed and influence major public events. For example, during the COVID-19 pandemic, a new blending of medical and political disinformation has given rise to the first global infodemic. We offer an overview of the emerging and inter-connected research areas of fact-checking, disinformation, "fake news'', propaganda, and media bias detection. We explore the general fact-checking pipeline and important elements thereof such as check-worthiness estimation, spotting previously fact-checked claims, stance detection, source reliability estimation, detection of persuasion techniques, and detecting malicious users in social media. We also cover large-scale pre-trained language models, and the challenges and opportunities they offer for generating and for defending against neural fake news. Finally, we discuss the ongoing COVID-19 infodemic.

Dimitar Dimitrov, Bishr Bin Ali, Shaden Shaar, Firoj Alam, Fabrizio Silvestri, Hamed Firooz, Preslav Nakov, Giovanni Da San Martino. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

The reporting and the analysis of current events around the globe has expanded from professional, editor-lead journalism all the way to citizen journalism. Nowadays, politicians and other key players enjoy direct access to their audiences through social media, bypassing the filters of official cables or traditional media. However, the multiple advantages of free speech and direct communication are dimmed by the misuse of media to spread inaccurate or misleading claims. These phenomena have led to the modern incarnation of the fact-checker --- a professional whose main aim is to examine claims using available evidence and to assess their veracity. Here, we survey the available intelligent technologies that can support the human expert in the different steps of her fact-checking endeavor. These include identifying claims worth fact-checking, detecting relevant previously fact-checked claims, retrieving relevant evidence to fact-check a claim, and actually verifying a claim. In each case, we pay attention to the challenges and the potential impact on real-world fact-checking.

During a disaster event, images shared on social media helps crisis managers gain situational awareness and assess incurred damages, among other response tasks. Recent advances in computer vision and deep neural networks have enabled the development of models for real-time image classification for a number of tasks, including detecting crisis incidents, filtering irrelevant images, classifying images into specific humanitarian categories, and assessing the severity of damage. Despite several efforts, past works mainly suffer from limited resources (i.e., labeled images) available to train more robust deep learning models. In this study, we propose new datasets for disaster type detection, and informativeness classification, and damage severity assessment. Moreover, we relabel existing publicly available datasets for new tasks. We identify exact- and near-duplicates to form non-overlapping data splits, and finally consolidate them to create larger datasets. In our extensive experiments, we benchmark several state-of-the-art deep learning models and achieve promising results. We release our datasets and models publicly, aiming to provide proper baselines as well as to spur further research in the crisis informatics community.

People increasingly use microblogging platforms such as Twitter during natural disasters and emergencies. Research studies have revealed the usefulness of the data available on Twitter for several disaster response tasks. However, making sense of social media data is a challenging task due to several reasons such as limitations of available tools to analyse high-volume and high-velocity data streams, dealing with information overload, among others. To eliminate such limitations, in this work, we first show that textual and imagery content on social media provide complementary information useful to improve situational awareness. We then explore ways in which various Artificial Intelligence techniques from Natural Language Processing and Computer Vision fields can exploit such complementary information generated during disaster events. Finally, we propose a methodological approach that combines several computational techniques effectively in a unified framework to help humanitarian organisations in their relief efforts. We conduct extensive experiments using textual and imagery content from millions of tweets posted during the three major disaster events in the 2017 Atlantic Hurricane season. Our study reveals that the distributions of various types of useful information can inform crisis managers and responders and facilitate the development of future automated systems for disaster management.

The success of deep neural networks (DNNs) is heavily dependent on the availability of labeled data.However, obtaining labeled data is a big challenge in many real-world problems.In such scenarios, a DNN model can leverage labeled and unlabeled data from a related domain, but it has to deal with the shift in data distributions between the source and the target domains.In this paper, we study the problem of classifying social media posts during a crisis event (e.g., Earthquake).For that, we use labeled and unlabeled data from past similar events (e.g., Flood) and unlabeled data for the current event.We propose a novel model that performs adversarial learning based domain adaptation to deal with distribution drifts and graph based semi-supervised learning to leverage unlabeled data within a single unified deep learning framework.Our experiments with two real-world crisis datasets collected from Twitter demonstrate significant improvements over several baselines.

The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness as disaster unfolds. In addition to textual content, people post overwhelming amounts of imagery content on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in computer vision research, making sense of the imagery content in real-time during disasters remains a challenging task. One of the important challenges is that a large proportion of images shared on social media is redundant or irrelevant, which requires robust filtering mechanisms. Another important challenge is that images acquired after major disasters do not share the same characteristics as those in large-scale image collections with clean annotations of well-defined object categories such as house, car, airplane, cat, dog, etc., used traditionally in computer vision research. To tackle these challenges, we present a social media image processing pipeline that combines human and machine intelligence to perform two important tasks: (i) capturing and filtering of social media imagery content (i.e., real-time image streaming, de-duplication, and relevancy filtering); and (ii) actionable information extraction (i.e., damage severity assessment) as a core situational awareness task during an on-going crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.

We present an end-to-end social media image processing system called Image4Act. The system aims at collecting, denoising, and classifying imagery content posted on social media platforms to help humanitarian organizations in gaining situational awareness and launching relief operations. It combines human computation and machine learning techniques to process high-volume social media imagery content in real time during natural and human-made disasters. To cope with the noisy nature of the social media imagery data, we use a deep neural network and perceptual hashing techniques to filter out irrelevant and duplicate images. Furthermore, we present a specific use case to assess the severity of infrastructure damage incurred by a disaster. The evaluations of the system on existing disaster datasets as well as a real-world deployment during a recent cyclone prove the effectiveness of the system.

In this paper, we aim to investigate the coordination of interlocutors behavior in different emotional segments. Conversational coordination between the interlocutors is the tendency of speakers to predict and adjust each other accordingly on an ongoing conversation. In order to find such a coordination, we investigated 1) lexical similarities between the speakers in each emotional segments, 2) correlation between the interlocutors using psycholinguistic features, such as linguistic styles, psychological process, personal concerns among others, and 3) relation of interlocutors turn-taking behaviors such as competitiveness. To study the degree of coordination in different emotional segments, we conducted our experiments using real dyadic conversations collected from call centers in which agent’s emotional state include empathy and customer’s emotional states include anger and frustration. Our findings suggest that the most coordination occurs between the interlocutors inside anger segments, where as, a little coordination was observed when the agent was empathic, even though an increase in the amount of non-competitive overlaps was observed. We found no significant difference between anger and frustration segment in terms of turn-taking behaviors. However, the length of pause significantly decreases in the preceding segment of anger where as it increases in the preceding segment of frustration.

Behavioral analytics is an emerging research area that aims at automatic understanding of human behavior. For the advancement of this research area, we are interested in the problem of learning the personality traits from spoken data. In this study, we investigated the contribution of different types of speech features to the automatic recognition of Speaker Personality Trait (SPT) across diverse speech corpora (broadcast news and spoken conversation). We have extracted acoustic, linguistic, and psycholinguistic features and modeled their combination as input to the classification task. For the classification, we used Sequential Minimal Optimization for Support Vector Machine (SMO) together with Relief feature selection. The present study shows different levels of performance for automatically selected feature sets, and overall improved performance with their combination across diverse corpora.

Natural human-computer interaction requires, in addition to understand what the speaker is saying, recognition of behavioral descriptors, such as speaker’s personality traits (SPTs). The complexity of this problem depends on the high variability and dimensionality of the acoustic, lexical and situational context manifestations of the SPTs. In this paper, we present a comparative study of automatic speaker personality trait recognition from speech corpora that differ in the source speaking style (broadcast news vs. conversational) and experimental context. We evaluated different feature selection algorithms such as information gain, relief and ensemble classification methods to address the high dimensionality issues. We trained and evaluated ensemble methods to leverage base learners, using three different algorithms such as SMO (Sequential Minimal Optimization for Support Vector Machine), RF (Random Forest) and Adaboost. After that, we combined them using majority voting and stacking methods. Our study shows that, performance of the system greatly benefits from feature selection and ensemble methods across corpora.