Test Case Generation for Dialogflow Task-Based Chatbots

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rapisarda, Rocco Gianni, Ginelli, Davide, Clerissi, Diego, Mariani, Leonardo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913724582854656
author Rapisarda, Rocco Gianni
Ginelli, Davide
Clerissi, Diego
Mariani, Leonardo
author_facet Rapisarda, Rocco Gianni
Ginelli, Davide
Clerissi, Diego
Mariani, Leonardo
contents Chatbots are software typically embedded in Web and Mobile applications designed to assist the user in a plethora of activities, from chit-chatting to task completion. They enable diverse forms of interactions, like text and voice commands. As any software, even chatbots are susceptible to bugs, and their pervasiveness in our lives, as well as the underlying technological advancements, call for tailored quality assurance techniques. However, test case generation techniques for conversational chatbots are still limited. In this paper, we present Chatbot Test Generator (CTG), an automated testing technique designed for task-based chatbots. We conducted an experiment comparing CTG with state-of-the-art BOTIUM and CHARM tools with seven chatbots, observing that the test cases generated by CTG outperformed the competitors, in terms of robustness and effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05561
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Test Case Generation for Dialogflow Task-Based Chatbots
Rapisarda, Rocco Gianni
Ginelli, Davide
Clerissi, Diego
Mariani, Leonardo
Software Engineering
Chatbots are software typically embedded in Web and Mobile applications designed to assist the user in a plethora of activities, from chit-chatting to task completion. They enable diverse forms of interactions, like text and voice commands. As any software, even chatbots are susceptible to bugs, and their pervasiveness in our lives, as well as the underlying technological advancements, call for tailored quality assurance techniques. However, test case generation techniques for conversational chatbots are still limited. In this paper, we present Chatbot Test Generator (CTG), an automated testing technique designed for task-based chatbots. We conducted an experiment comparing CTG with state-of-the-art BOTIUM and CHARM tools with seven chatbots, observing that the test cases generated by CTG outperformed the competitors, in terms of robustness and effectiveness.
title Test Case Generation for Dialogflow Task-Based Chatbots
topic Software Engineering
url https://arxiv.org/abs/2503.05561