Indexing, enriching, and understanding Brazilian missing person cases from data of distributed repositories on the web

Abstract For decision making in government, it is necessary to have well-structured sources of information. In several countries, difficult access government data as the information are dispersed, disconnected, and poorly structured. this reason, work presents a framework gather, unify, enrich missing person from distributed web sources. The allows inserting new tasks specific user’s domain improve quality. study, Brazilian non-governmental organizations (NGOs) governmental websites were collected semantically enriched. To enhance understanding gathered people cases, we create interpretive models using machine learning techniques extract knowledge encourage use standards for publishing that frequently ignored by organizations, hindering analysis decision-making on data. After collection semantic enrichment process, there was an increase approximately 11% present base. Also, mining process evidenced disappearance reappearance Brazil according factors such age, state initiatives, skin tone, hair colors, etc.