Systematic Literature Review
Systematic literature reviews (SLRs) are rigorous research methodologies used to synthesize existing knowledge on a specific topic, aiming to provide a comprehensive and unbiased overview of the current state of research. Recent studies highlight the increasing use of AI, particularly large language models (LLMs) and deep learning architectures, to automate various stages of the SLR process, from literature searching and screening to data extraction and synthesis. This automation offers significant potential for improving efficiency and reducing bias in research, impacting diverse fields from software engineering and healthcare to cybersecurity and agriculture, where evidence-based decision-making is crucial. Furthermore, research emphasizes the need for transparency and explainability in AI-driven SLRs, ensuring the reliability and trustworthiness of the resulting knowledge synthesis.
Papers
Rule-Extraction Methods From Feedforward Neural Networks: A Systematic Literature Review
Sara El Mekkaoui, Loubna Benabbou, Abdelaziz Berrado
Human-Centred Learning Analytics and AI in Education: a Systematic Literature Review
Riordan Alfredo, Vanessa Echeverria, Yueqiao Jin, Lixiang Yan, Zachari Swiecki, Dragan Gašević, Roberto Martinez-Maldonado
Spherical Rolling Robots Design, Modeling, and Control: A Systematic Literature Review
Aminata Diouf, Bruno Belzile, Maarouf Saad, David St-Onge
Automatic Quality Assessment of Wikipedia Articles -- A Systematic Literature Review
Pedro Miguel Moás, Carla Teixeira Lopes
Data Cleaning and Machine Learning: A Systematic Literature Review
Pierre-Olivier Côté, Amin Nikanjam, Nafisa Ahmed, Dmytro Humeniuk, Foutse Khomh