X-SSAS: human-machine interaction-driven framework for explainable and scalable similarity-based link prediction in social networks

Key Points

• This work aims to establish a scalable and explainable framework for link prediction in social networks using human-machine interaction.
• Developed a human-machine interaction model for link prediction.
• Utilized similarity-based measures to enhance predictive capability.
• Tested the model in various social network scenarios.
• Demonstrated improved prediction accuracy over traditional methods.
• Increased user comprehension of prediction rationale through explainable outputs.

Abstract