March 31 2023: Tahaqqaq demo paper is accepted at SIGIR 2023!
March 6 2023: Tahaqqaq is presented at AlJazeera "AI in Media" Conference
Tahaqqaq (meaning "Verify" in Arabic) is an experimental real-time system that helps users verify spreading claims expressed in plain text or tweets or even Twitter search results. It provides multiple services, e.g., whether the tweet is check-worthy, veracity of the claim/tweet, credibility of the Twitter user, whether the claim was previously-verified, and authority accounts relevant to the claim.
تَحَقَّق هو تطبيق تجريبي يساعد المستخدمين العرب على التحقق من الادعاءات المنتشرة والمعبر عنها في نص عادي أو تغريدات أو حتى نتائج بحث على تويتر. يوفر التطبيق خدمات متعددة، منها ما إذا كانت التغريدة جديرة بالتحقق، وقياس مدى صحة الادعاء فيها، ومصداقية كاتبها، وما إذا كان قد تم التحقق من الادعاء مسبقًا، وسرد الحسابات ذات الصلة التي يمكن التحقق من خلالها.
Over the past years, notable progress has been made towards fighting misinformation spread over social media, encouraging the development of many fact-checking systems. However, systems that operate over Arabic content are scarce. In this work, we bridge this gap by proposing Tahaqqaq (Verify), an Arabic real-time system that helps users verify claims over Twitter with several functionalities, such as identifying check-worthy claims, estimating credibility of users in terms of spreading fake news, and finding authoritative accounts. Tahaqqaq has a friendly online Web interface that supports various real-time user scenarios. In the same breath, we enable public access to Tahaqqaq services through a handy RESTful API. Finally, in terms of performance, multiple components of Tahaqqaq outperform the state-of-the-art models on Arabic datasets.
Tahaqqaq is completely designed and developed at Qatar University by the talent of a research team of members of bigIR research group (Zien Sheikh Ali, Watheq Mansour, Fatima Haouari, and Maram Hasanain) under the supervision of Dr. Tamer Elsayed and in collaboration with Dr. Abdulaziz Al-Ali. The project is funded by QNRF under research grant NPRP11S-1204-170060.
Tahaqqaq is a Web-based system built using Flask framework. The online user interface allows users to explore different use cases. We also expose our fact-checking functionalities as a RESTful API that accepts POST and GET requests from the user, making it accessible through any programming language. The complete pipeline of our proposed system is depicted here. The system encompasses three stages: Claim Detection, Claim Retrieval, and Claim Checking.
Tahaqqaq pipeline and components
Experimental Live Demo: http://bigir1.qu.edu.qa:5050/tahaqqaq
API: https://gitlab.com/bigirqu/Tahaqqaq
Quick Video: https://drive.google.com/file/d/1tJKdnb58mBMO5YeTklUfVXy3ZvoEmdwS/view
Zien Sheikh Ali, Watheq Mansour, Fatima Haouari, Maram Hasanain, Tamer Elsayed, Abdulaziz Al-Ali. Tahaqqaq: A Real-Time System for Assisting Twitter Users in Arabic Claim Verification. Proceedings of the 46th Annual ACM International Conference on Research and Development in Information Retrieval: SIGIR '23, Taiwan, July 2023.