With the increasing complexity of web applications, the need for comprehensive and effective automated testing has become more important than ever. This paper reviews and analyzes recent approaches to automated testing of web applications using artificial intelligence algorithms, including machine learning, deep learning, and neural networks. After examining the challenges of traditional web testing, such as dynamic forms and complex logic, intelligent methods are introduced in three main categories:
(1) machine learning for test case generation and analysis
(2) neural networks and deep learning for understanding user interface elements and performing automated testing.
(3) deep reinforcement learning for autonomous exploration of the web state space.
Examples of selected frameworks, such as WebRLED and WebExplor, are presented along with their experimental results. The findings indicate that AI-based methods can significantly improve code coverage and fault detection rates. Future research directions include the integration of Large Language Models (LLMs) and broader access to real-world datasets for modern training.
Article Link:
