MediBot: A chatbot for risk and information consultation on medicines

• Caio Viktor S. Avila UFC
• Tulio Vidal Rolim UFC
• José Wellington Franco da Silva UFC
• Vania Maria Ponte Vidal UFC

DOI: https://doi.org/10.5753/sbcas.2019.6275

Abstract

Self-medication without medical advice can lead to health problems through intoxication. The objective of this study is to present MediBot - a chat- bot to consult information about medications and their risks. MediBot enables queries through natural language, transformed them into SPARQL queries over a Linked Data Mashup about data on medicines provided by ANVISA and Sider sources. Finally, MediBot presents itself as a timely tool in promoting access to information by the general public.

References

Belleau, F. et al. (2008). Bio2rdf: towards a mashup to build bioinformatics knowledge systems. Journal of biomedical informatics, 41(5):706–716.

Bizer, C. et al. (2011). Linked data: The story so far. In Semantic services, interoperability and web applications: emerging concepts, pages 205–227. IGI Global.

Corrêa, A. et al. (2013). Uma abordagem sobre o uso de medicamentos nos livros

didáticos de biologia como estratégia de promoção de saúde. Ciência & Saúde Coletiva, 18:3071–3081.

Shadbolt, N. et al. (2006). The semantic web revisited. IEEE intelligent systems, 21(3):96–101.

SINITOX (2016). Sistema Nacional de Informações Toxicológicas registro de intoxicações no brasil. Acessado: 10-02-2019.

WHO et al. (2002). Safety of medicines: a guide to detecting and reporting adverse drug reactions. Technical report, Geneva: World Health Organization.