We introduce Domain Shift across Geographic Regions (DSGR), a new large-scale dataset designed to study the effects of real-world geospatial distribution shifts in satellite imagery classification. DSGR captures variability across diverse geographic regions, with particular emphasis on underrepresented areas such as Africa and Oceania, enabling systematic analysis of how regional…
AIDR—the Grand Prize winner of the 2015 Open Source Software System Challenge—is a free and open platform to filter and classify social media messages related to emergencies, disasters, and humanitarian crises. AIDR uses human and machine intelligence to automatically tag up to thousands of messages per minute. https://aidr.qcri.org
Experience AI-enhanced education with Cipherbot, a platform for teachers and students. Cipherbot, an AI chatbot, allows students to ask questions and get answers directly from their class materials, transforming static learning into dynamic dialogue. https://cipherbot.qcri.org https://cipherbot.qcri.org/pitch/Cipherbot%20Pitch.pdf
METRIC is a tool for collecting, measuring, analyzing, and reporting the engagement of online systems through real interactions of customers or users, including real-time. METRIC enables system stakeholders to enhance understanding of their customers via actual behavior on particular pages in the online systems, including the focus and interaction with…
Survey2Persona is a survey data analysis and visualization tool. It transforms numerical survey responses (e.g., Likert scale, Binary, or other categorical data) and associate demographic survey data into personas, a humanized representation of the underlying survey data presented as a believable person, containing picture, name, age, country, and other demographic…
Acua is the organizing theme of our research efforts, focusing on audience, customer, and user analytics for an enhanced understanding of these populations for an organization. Our efforts concentrate on research for collecting, measuring, analyzing, and reporting digital data to enhance insights into the behavior of audiences, customers, and users,…
Object detectors achieve strong performance on benchmark datasets, yet most are trained under the i.i.d. assumption, leading to significant degradation when deployed under real-world distribution shifts. Domain Generalisation (DG) addresses this challenge by enabling models to generalise to unseen, Out-Of-Distribution data without access to target domains during training. However, evaluating…
Natural disasters, such as floods, tornadoes, or wildfires, are increasingly pervasive as the Earth undergoes global warming. It is difficult to predict when and where an incident will occur, so timely emergency response is critical to saving the lives of those endangered by destructive events. Fortunately, technology can play a…
The development of a system that monitors social media continuously for general landslide-related content using a landslide classification model to identify and retain the most relevant information is described and validated. The system harvests photographs in real-time from these data and tags each image as landslide or not-landslide. A training…
The Flood Insights Dashboard (FID) is a comprehensive tool for evaluating the immediate flood situation during the onset of a flood disaster. Using the best available data, methods and analytical tools, FID synthesizes satellite, social media and geospatial data to help guide crisis responders in making effective decisions. System: https://flood-insights.qcri.org/pakistan_floods_2022 Paper…
This visual shows reports of attacks on education in Africa and the Middle East from the Armed Conflict Location & Event Data Project (ACLED) as well as social media posts from Twitter about education insecurity identified by the Artificial Intelligence for Digital Response (AIDR) platform. The blue circles represent the number of tweets about…
The CrisisMMD multimodal Twitter dataset consists of several thousands of manually annotated tweets and images collected during seven major natural disasters including earthquakes, hurricanes, wildfires, and floods that happened in the year 2017 across different parts of the World. The provided datasets include three types of annotations. Dataset: https://crisisnlp.qcri.org/crisismmd