Leveraging User Activity Insights to Enhance Notifications Overload in a Knowledge-Sharing Platform

Abstract

This study explores user engagement patterns to improve a platform’s notification system and efficiency, designed to enhance knowledge sharing by enabling employees to contribute value through effective communication. As the platform grows, concerns about notification overload have increased due to the rising number of notifications. Using multiple linear regression and logistic regression models, the analysis revealed that users primarily engage within their declared interests, but also contribute significantly beyond these areas. These insights, combined with clustering analysis, help refine the platform’s auto-tagging feature and introduce a response threshold to better identify the "right" users for notifications. Future research will focus on cross-category engagement, exploring user response duration, and analysing activeness and responsiveness scores. Additionally, expanding the dataset across different organizations will uncover further behavioural patterns, allowing for more effective notification targeting, reducing overload, and improving the overall user experience.

DOI: https://doi.org/10.24135/ICONIP28