Deep Learning-Enhanced Adaptive Interface for Improved Accessibility in E-Government Platforms
Year: 2024
Type: conference-paper
Abstract: The advent of e-government platforms has highlighted the pressing need to enhance the accessibility of digital services for individuals with low literacy rates and special needs. The objective of this study is to design and develop an adaptive interface system utilising deep learning technology with the intention of markedly enhancing the accessibility and user-friendliness of e-government platforms, particularly for users with low literacy rates and special needs. The proposed model incorporates multimodal learning and reinforcement learning mechanisms, enabling automatic adjustments to the interface layout, text size, colour contrast and voice assistance functions to align with the personalised requirements of users. In particular, when integrated with sentiment analysis and speech recognition modules, the system is capable of identifying and predicting the user's operational intent in real time, thereby enabling dynamic interface adjustments. The model's innovative aspect lies in its adaptive adjustment capability and high efficiency in low-resource environments. The experimental results demonstrate that the proposed model can markedly enhance the operational efficiency and satisfaction of individuals with low literacy rates and special needs, while also improving the user experience.
Authors: Xiang Li, Yikan Wang
Institutions: Long Island University, Stevens Institute of Technology
Language: English
Subfield: Human Factors and Ergonomics
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W4408400556