Mozambique is a country in southern Africa, a former Portuguese colony, where almost 40% of girls and adolescents become pregnant before the age of 18. An enormous challenge in developing countries to overcome poverty is to ensure that girls do not become pregnant at an early age. To this end, various international organizations and NGOs are actively working in Africa to help the governments advance this agenda.
Currently, there are initiatives of support and sexual and reproductive education for girls, young women, and adolescents through digital media and SMS. In these media there is a dialogue between experts who guide and orient those who write, there are millions of conversations collected in recent years.
All these conversations contain unstructured data that are of great value to understand over time the evolution of the concerns of those who use these channels and how to use this information to make better public policy decisions by the government with international support.
Deep Talk analyzed these data using different deep learning models, structured and visualized them, from it was possible to extract analytics and metrics impossible to achieve through the traditional measurement of a conversation.
Some examples:
- Most frequent conversational clusters by girls.
- Most frequent conversational clusters by boys
- Most frequent conversational clusters according to geographic location.
- Training phrases for automating responses with the use of bots
- Search for key concepts within clusters
- Evolution over time of young people’s ideas, concepts, and concerns and how this occurred in the clusters detected.
The use of real conversations that young people have with the help centers made it possible to detect the differences in teenage pregnancy between women and men and the approach that each sex had to this problem through the questions asked. It was also possible to detect the approach to other topics such as AIDS, sexually transmitted diseases, or general questions and myths about sexuality.
All this analysis can only be done manually by reading and summarizing the millions of conversations (with an average of 10 to 12 messages per conversation) or through the use of deep learning models to structure the conversations and obtain metrics and analytics from them.
Conclusion
The analysis of real conversations between citizens and government or organizations that serve people in the areas of health, education, security, etc. through the application of deep learning models such as those used by Deep Talk, is a powerful tool for public policy by extracting relevant data for decision making directly from the conversation of a citizen and not through indirect methods.
These tools can be used for dozens of applications, from analyzing bullying in social networks, suicide prevention to using them to make better public policy decisions. It is important to note that these tools are actively used by large social networking companies and search engines, generating an asymmetry with governments in understanding what´s going on in the digital world.
