10.29327/1407529.27-19
Context: Chatbots are complex applications due to their capacity to engage and maintain a conversation with humans. However, the conversational-related requirements of chatbots are hard to elicit, document, and test. Another challenge is the documentation since there are not so many directions on how to register and test subjective requirements. Methods: We followed systematic literature review (SLR) guidelines and identified 42 relevant papers that address the artifacts used by practitioners to document conversational-related requirements in literature. We also investigated what conversational requirements are addressed in requirements documentation. Results: The main results indicate that UML diagrams, prototypes, tables of requirements, conversational flows, and scenarios are present in most chatbot documentation. Except for UML diagrams, those artifacts are used to document standard requirements or conversational requirements. In those artifacts, context-dependent behavior, assertivity, error handling, and human-like attitude are the most approached conversational requirements in the studies. In sequence, based on our findings, we propose the conversational integrated map, a meta-model solution as documentation of conversational requirements.
Chatbots conversational agents; specification conversational requirements; conversational integrated map
@inproceedings{wer202409,
author = {Gonçalves, L. P. and Silva, G. R. S. and Canedo, E. D.},
title = {Documentation Artifacts For Conversation-Related Requirements Specification in Chatbots},
booktitle = {Proceedings of the WER2024-27th Workshop on Requirements Engineering, Buenos Aires, Argentina},
year = {2024},
issn = {2675-0066},
isbn = {978-65-01-06131-3},
doi = {10.29327/1407529.27-19}
}