Augmented behavioral annotation tools, with application to multimodal datasets and models: A systematic review
Authors: E Watson, T Viana, S Zhang
Published: 2024
Publication: AI, 2023 - mdpi.com
The paper systematically reviews augmented behavioral annotation tools, focusing on their evolution, current state, and application to multimodal datasets and models, highlighting best practices and emerging challenges in safe and ethical annotation for large-scale multimodal systems.
Methods: Systematic literature review analyzing crowd and machine learning-augmented behavioral annotation methods, with cross-disciplinary comparisons and structured synthesis of practices.
Key Findings: Evolution of behavioral annotation tools, their integration with machine learning, emerging trends (e.g., prompt engineering), challenges in large multimodal datasets, and ethical and engineering best practices.
Limitations: Does not establish new experimental data or validated guidelines for multimodal system annotation; relies on existing literature and may lack real-world application testing.
Research Area: Behavioral Annotation Tools and Multimodal Data
Discipline: Computer Science
Citations: 17
DOI: https://doi.org/10.3390/ai4010007