Creating an Academic Conversational Agent for Dynamic Information Retrieval

• João Cruz UFSJ
• Millas Nasser Avelar UFSJ
• Matheus Carvalho Viana UFSJ
• Elisa Tuler Albergaria UFSJ
• Dárlinton Carvalho UFSJ
• Leonardo Rocha UFSJ

DOI: https://doi.org/10.5753/sbsi.2020.13781

Resumo

The popularization and evolution of online conversational agents, also known as chatbots, provoked disruptive changes in the communication between institutions and people. Motivated by the growing need to provide more efficient mechanisms for information retrieval from legislation, manuals, and operational procedures, as well as taking advantage of recent technological developments, we propose an architectural model for conversational agents specialized in institutional information retrieval from unstructured documents (e.g., PDFs, DOCX). Besides, we present a conversational agent, created from our architectural model, to assist in the search and retrieve for information related to resolutions and internal regulations at our university. An evaluation performed with users using the System Usability Score (SUS) method revealed that our conversational agent presented itself as an effective alternative, achieving almost the best imaginable usability (SUS Score 89), and speeding up the search and retrieval for institutional information.

Palavras-chave: architectural model, conversational agent, information retrieval, chatbot