This is your work, valued
Research interests: NLP, Speech and Machine learning; Disinformation, Emotion, Sentiment, Social media, Humanitarian Informatics, Bangla NLP
multimodal_social_media. multimodal social media content (text, image) classification
53harmful-memes-detection-resources. Resources (conference/journal publications, references to dataset) for harmful memes detection.
52crisis_datasets_benchmarks. Crisis Dataset for Benchmarks Experiments
25medic. Multi-Task Learning for Disaster Image Classification using MEDIC
25domain-adaptation. Domain Adaptation with Adversarial Training and Graph Embeddings
15COVID-19-tweets-for-check-worthiness. COVID-19 Infodemic Twitter dataset
13COVID-19-disinformation. Dataset: Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society
12LlamaLens. This repository contains the resources, code, and documentation for LlamaLens, a specialized multilingual large language model (LLM) designed to analyze news and social media content effectively. LlamaLens supports multiple languages, including Arabic, English, and Hindi, and is tailored for diverse tasks such as sentiment analysis, misinformation.
9openSMILE-configuration. openSMILE configuration files for the acoustic feature extraction of emotion recognition.
3Detecting-Previously-Fact-Checked-Claims. Role of Context in Detecting Previously Fact-Checked Claims
3crisis-embedding-models. Embedding models designed using crisis related tweets collected by AIDR (http://aidr.qcri.org/)
3covid19-infodemic-demo. API Services: Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society
2QCRI-Automatic-Report-Generator-for-Disaster-Events-ARGDE. JavaScript
1assisting-fact-checking. Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document
1nlp. :memo: This repository recorded my NLP journey.
1nativqa-framework. NativQA Framework collects multilingual, culturally aligned natural queries and QA pairs from real-world local search, making it easy to build region-specific QA datasets for LLM evaluation and tuning.
1TAADpapers. Must-read Papers on Textual Adversarial Attack and Defense
1LLMeBench. Benchmarking Large Language Models
1