This project has two components. First, it conducts social media listening exercises in Africa to understand conversations related to COVID-19 and poliovirus. Second, it supports research to test interventions to reduce vaccine hesitancy among social media users using machine learning.
Activity Type Research/Reports/AssessmentsAwareness/AdvocacyThis project aims to calculate and anticipate the number of displaced persons crossing the Brazil-Venezuela border to understand their need for humanitarian support. It consists of a queue modeling tool, a nowcasting effort using big data, and predictive models for forecasting future movements.
Activity Type AI Tools/SolutionsResearch/Reports/AssessmentsThis project uses an AI-powered public radio social listening tool to mine data on perceptions around Gender Based Violence (GBV), Violence Against Women and Girls (VAWG), Harmful Practices (HP), Sexual Reproductive Health Rights (SRHR), and Violence Against Children (VAC). The data provides insights for timely and targeted interventions. Radio remains the most popular source of information in Uganda, used by different people irrespective of their demographics. Radio shows allow two-way communication between radio studios and people in the community through call-ins, making them a rich representation of the people that are digitally marginalized.
Activity Type AI Tools/SolutionsResearch/Reports/AssessmentsA radio monitoring pipeline was developed to 'listen' to online radio stations, transcribe the audio using machine learning speech-to-text models, and analyze the content using NLP methods. The dashboard is used by infodemic managers and decision-makers to inform public health interventions.
Activity Type AI Tools/SolutionsResearch/Reports/Assessments