Banca de DEFESA: JOELDSON COSTA DAMASCENO

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : JOELDSON COSTA DAMASCENO
DATE: 09/04/2024
TIME: 14:00
LOCAL: https://meet.google.com/fwb-dwsh-vhi
TITLE:

REQUIREMENTS ENGINEERING AIDED BY SMART CHATBOTS: AN ASSESSMENT OF THE QUALITY OF ARTIFACTS

KEY WORDS:

Requirements Engineering; Generative Artificial Intelligence; Smart Chatbot; Requirements Artifacts; Requirements Specification.

PAGES: 240
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUMMARY:

Requirements Engineering is an essential process of collecting, documenting, and maintaining software requirements aligned with business objectives. The requirements elicitation phase is the starting point of software development, and it is a crucial, complex and time-consuming activity. To perform this role, professionals require specific skills such as effective communication, analytical reasoning, empathy, conflict resolution skills, moderation, self-confidence and persuasion. Unfortunately, there is a significant shortage of specialized professionals that has negatively impacted production, especially the quality of deliveries. Statistics reveal a considerable number of failures in software products due to problems in the requirements engineering stage. However, recent research points to the promising use of generative artificial intelligence as a solution to improve requirements engineering. Artificial intelligence tools have the potential to automate tasks such as requirements gathering and analysis, as well as assist in identifying and correcting ambiguous or incomplete requirements. In this study, our objective was to evaluate how requirements professionals perceive the application of a generative AI chatbot in requirements specification, taking into account the exploration of the ideal approach for preparing the prompt and evaluating the quality of the resulting artifacts. As a result, despite the prompt strategies developed by the participants, the experiment did not result in the production of artifacts with satisfactory quality for application in real projects in the context of requirements specification. However, the tool proved to be useful for professionals to explore previously unconsidered requirements, highlighting its usefulness for brainstorming in requirements elicitation. And as a major contribution, the experiment generated relevant practical recommendations for formatting prompts for requirements specification. It is expected that this modest contribution will serve to improve practices in the area of Requirements Engineering when employing new AI technologies.

COMMITTEE MEMBERS:
Presidente - 2978747 - CHARLES ANDRYE GALVAO MADEIRA
Interno - 2180207 - ITAMIR DE MORAIS BARROCA FILHO
Externo ao Programa - 1671962 - EDUARDO HENRIQUE DA SILVA ARANHA - UFRNExterna ao Programa - 2245086 - ISABEL DILLMANN NUNES - UFRNExterno à Instituição - GEBER LISBOA RAMALHO - UFPE