Leveraging User Activity Insights to Enhance Notifications Overload in a Knowledge-Sharing Platform
Loading...
Files
Size: 226.11 KB, File format: Adobe PDF
Size: 3.8 MB, File format: Adobe PDF
Date
Authors
Zar, Moe Thu
Mohaghegh, Mahsa
Supervisor
Item type
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
International Conference on Neural Information Processing (ICONIP)
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.
Description
Keywords
Source
M Mahmud, M Doborjeh, N Kasabov, Z Doborjeh (Eds.) Peer-Reviewed Abstracts of the 31st International Conference on Neural Information Processing (ICONIP 2024), 2-6 Dec 2024, Auckland, New Zealand. DOI: https://doi.org/10.24135/ICONIP28
DOI
Publisher's version
Rights statement
© CC BY-NC-SA 4.0, The Author(s)
Permanent link
Collections
Endorsement
Review
Supplemented By
Referenced By
Creative Commons license
Except where otherwise noted, this item's license is described as © CC BY-NC-SA 4.0, The Author(s)