United Nations Population Fund (UNFPA)


UNFPA is the United Nations sexual and reproductive health agency. Our mission is to deliver a world where every pregnancy is wanted, every childbirth is safe and every young person’s potential is fulfilled.

Description of Activities on AI

Project 1: ECHO: Amplifying citizen’s voices for the SDGs”

ECHO is a unique tool that uses Automatic Speech Recognition, Cognitive Computing, and Data Analytics to improve the efficiency in processing large amounts of information in real-time. ECHO collects information from individuals of all backgrounds, including minorities and vulnerable populations

ECHO is a tool powered by artificial intelligence that promotes citizens’ participatory planning and awareness about the SDGs through real-time guided public discussion. ECHO is seeking to link conversational and informal citizen’s language to SDGs language using a classification model, developed by UNFPA Colombia.

Project 2: Social Media Data Tracker (SMDT)

SMDT is a tool for scraping and identifying myths related to Sexual and Reproductive Health in social networks. Using natural language processing technologies, visual image processing and complex graph construction, SMDT is able to identify groups, users, themes, threads, etc., close and vulnerable to SRH myths.

SMDT is a project that seeks to scratch data from the social media, particularly tweets generated around sexual and reproductive health, including ideas about right and wrong ways to prevent pregnancy, and notions about relationships and contraceptive use. With the help of AI, specifically with Natural Language Processing, we could understand what people are thinking about the myths and misconceptions about contraceptive use. With the use of Natural Language Processing (NLP), we can structure this information, thus quantifying all the data collected (scraped).

With the use of image processing, and adding entity recognition data, we can get a very good focus on what is the belief about some contraceptives and what entities are related to those beliefs. With this knowledge generated, we can make the design of interventions and behavior change campaigns more specific and effective in getting people to change misconceptions about contraceptive methods.

Currently within the project we have been able to scratch more than 800,000 tweets related to Sexual and Reproductive Health, and have processed more than a third of them, finding myths and beliefs (SRH related) there.

Related Sustainable Development Goals (SDGs)

Scroll Up