Human-centric and Semantics-based Explainable Event Detection: A Survey

Abstract

In recent years, there has been a surge in interest in artificial intelligent systems that can provide human-centric explanations for decisions or predictions. No matter how good and efficient a model is, users or practitioners find it difficult to trust such model if they cannot understand the model or its behaviours. Incorporating explainability that is human-centric in event detection systems is significant for building a decision-making process that is more trustworthy and sustainable. Human-centric and semantics-based explainable event detection will achieve trustworthiness, explainability, and reliability, which are currently lacking in AI systems. This paper provides a survey on the human-centric explainable AI, explainable event detection, and semantics-based explainable event detection by answering some research questions that bother on the characteristics of human-centric explanations, the state of explainable AI, methods for human-centric explanations, the essence of human-centricity in explainable event detection, research efforts in explainable event solutions, and the benefits of integrating semantics into explainable event detection. The findings from the survey show the current state of human-centric explainability, the potential of integrating semantics into explainable AI, the open problems, and the future directions which can serve as steppingstones for researchers in the explainable AI domain.

Explainable AI: Bridging the Gap between Machine Learning Models and Human Understanding

“…According to the Kolajo and Daramola paper (2023), scholars examined both human-centric and semantics based explainable event detection models. The paper evaluated these techniques by presenting ways on how an AI system semantic linguistic and user centered design principles could be improved so that the interpretability of event driven AI system could be enhanced [23]. Lukomski et al (in the year 2024) studied the effect of oncological data on the AI predictions of five years survival in esophageal cancer, which is a proof of the necessity of interpretable AI models for clinical decision support and personalized medicine [24].…”