A Modeling Strategy for the Verification of Context-Oriented Chatbot Conversational Flows via Model Checking

Verification of chatbot conversational flows is paramount to capturing and understanding chatbot behavior and predicting problems that would cause the entire flow to be restructured from scratch. The literature on chatbot testing is scarce, and the few works that approach this subject do not focus o...

Full description

Bibliographic Details
Main Authors: Geovana Ramos Sousa Silva, Genaína Nunes Rodrigues, Edna Dias Canedo
Format: Article
Language:English
Published: Graz University of Technology 2023-07-01
Series:Journal of Universal Computer Science
Subjects:
Online Access:https://lib.jucs.org/article/91311/download/pdf/
_version_ 1827890653467508736
author Geovana Ramos Sousa Silva
Genaína Nunes Rodrigues
Edna Dias Canedo
author_facet Geovana Ramos Sousa Silva
Genaína Nunes Rodrigues
Edna Dias Canedo
author_sort Geovana Ramos Sousa Silva
collection DOAJ
description Verification of chatbot conversational flows is paramount to capturing and understanding chatbot behavior and predicting problems that would cause the entire flow to be restructured from scratch. The literature on chatbot testing is scarce, and the few works that approach this subject do not focus on verifying the communication sequences in tandem with the functional requirements of the conversational flow itself. However, covering all possible conversational flows of context-oriented chatbots through testing is not feasible in practice given the many ramifications that should be covered by test cases. Alternatively, model checking provides a model-based verification in a mathematically precise and unambiguous manner. Moreover, it can anticipate design flaws early in the software design phase that could lead to incompleteness, ambiguities, and inconsistencies. We postulate that finding design flaws in chatbot conversational flows via model checking early in the design phase may overcome quite a few verification gaps that are not feasible via current testing techniques for context-oriented chatbot conversational flows. Therefore, in this work, we propose a modeling strategy to design and verify chatbot conversational flows via the Uppaal model checking tool. Our strategy is materialized in the form of templates and a mapping of chatbot elements into Uppaal elements. To evaluate this strategy, we invited a few chatbot developers with different levels of expertise. The feedback from the participants revealed that the strategy is a great ally in the phases of conversational prototyping and design, as well as helping to refine requirements and revealing branching logic that can be reused in the implementation phase.
first_indexed 2024-03-12T21:12:42Z
format Article
id doaj.art-309285c9c73547dc98418aaeb2e30290
institution Directory Open Access Journal
issn 0948-6968
language English
last_indexed 2024-03-12T21:12:42Z
publishDate 2023-07-01
publisher Graz University of Technology
record_format Article
series Journal of Universal Computer Science
spelling doaj.art-309285c9c73547dc98418aaeb2e302902023-07-30T08:11:06ZengGraz University of TechnologyJournal of Universal Computer Science0948-69682023-07-0129780583510.3897/jucs.9131191311A Modeling Strategy for the Verification of Context-Oriented Chatbot Conversational Flows via Model CheckingGeovana Ramos Sousa Silva0Genaína Nunes Rodrigues1Edna Dias Canedo2University of BrasíliaUniversity of BrasíliaUniversity of BrasíliaVerification of chatbot conversational flows is paramount to capturing and understanding chatbot behavior and predicting problems that would cause the entire flow to be restructured from scratch. The literature on chatbot testing is scarce, and the few works that approach this subject do not focus on verifying the communication sequences in tandem with the functional requirements of the conversational flow itself. However, covering all possible conversational flows of context-oriented chatbots through testing is not feasible in practice given the many ramifications that should be covered by test cases. Alternatively, model checking provides a model-based verification in a mathematically precise and unambiguous manner. Moreover, it can anticipate design flaws early in the software design phase that could lead to incompleteness, ambiguities, and inconsistencies. We postulate that finding design flaws in chatbot conversational flows via model checking early in the design phase may overcome quite a few verification gaps that are not feasible via current testing techniques for context-oriented chatbot conversational flows. Therefore, in this work, we propose a modeling strategy to design and verify chatbot conversational flows via the Uppaal model checking tool. Our strategy is materialized in the form of templates and a mapping of chatbot elements into Uppaal elements. To evaluate this strategy, we invited a few chatbot developers with different levels of expertise. The feedback from the participants revealed that the strategy is a great ally in the phases of conversational prototyping and design, as well as helping to refine requirements and revealing branching logic that can be reused in the implementation phase.https://lib.jucs.org/article/91311/download/pdf/chatbotsformal verificationconversational desi
spellingShingle Geovana Ramos Sousa Silva
Genaína Nunes Rodrigues
Edna Dias Canedo
A Modeling Strategy for the Verification of Context-Oriented Chatbot Conversational Flows via Model Checking
Journal of Universal Computer Science
chatbots
formal verification
conversational desi
title A Modeling Strategy for the Verification of Context-Oriented Chatbot Conversational Flows via Model Checking
title_full A Modeling Strategy for the Verification of Context-Oriented Chatbot Conversational Flows via Model Checking
title_fullStr A Modeling Strategy for the Verification of Context-Oriented Chatbot Conversational Flows via Model Checking
title_full_unstemmed A Modeling Strategy for the Verification of Context-Oriented Chatbot Conversational Flows via Model Checking
title_short A Modeling Strategy for the Verification of Context-Oriented Chatbot Conversational Flows via Model Checking
title_sort modeling strategy for the verification of context oriented chatbot conversational flows via model checking
topic chatbots
formal verification
conversational desi
url https://lib.jucs.org/article/91311/download/pdf/
work_keys_str_mv AT geovanaramossousasilva amodelingstrategyfortheverificationofcontextorientedchatbotconversationalflowsviamodelchecking
AT genainanunesrodrigues amodelingstrategyfortheverificationofcontextorientedchatbotconversationalflowsviamodelchecking
AT ednadiascanedo amodelingstrategyfortheverificationofcontextorientedchatbotconversationalflowsviamodelchecking
AT geovanaramossousasilva modelingstrategyfortheverificationofcontextorientedchatbotconversationalflowsviamodelchecking
AT genainanunesrodrigues modelingstrategyfortheverificationofcontextorientedchatbotconversationalflowsviamodelchecking
AT ednadiascanedo modelingstrategyfortheverificationofcontextorientedchatbotconversationalflowsviamodelchecking