Author(s):
1. Umme Habia:
University of Engineering and Technology, Taxila, Pakistan
2. Mubbshir Ayub:
University of Engineering and Technology, Taxila, Pakistan
Abstract:
In the field of recommender systems, the role of trust between users has become crucial for improving the personalization and quality of recommendations. This research ventures into the sphere of trust-based recommendation systems, introducing an innovative implicit trust metric that specifically addresses the shortcomings of current metrics. Our proposed metric is meticulously crafted to embrace essential trust properties, with a special emphasis on context dependence, alongside asymmetry and transitivity, leading to notably enhanced recommendation outcomes. The unique focus on context dependence allows our metric to reflect the dynamic nature of user preferences and situations more accurately, thereby achieving superior accuracy in recommendations. Through detailed empirical analysis, we validate the significant impact of our context-aware trust metric, demonstrating its capability to elevate the precision and relevance of recommendations across a variety of settings. This research not only underscores the importance of incorporating context into trust evaluations but also sets a new standard for the effectiveness of recommendation systems.
Page(s):
1-1
DOI:
DOI not available
Published:
Journal: Second International Conference on Computing Technologies, Tools and Applications (ICTAPP-24), June 4-6,2024 (Abstract Book), Volume: 0, Issue: 0, Year: 2024
Keywords:
Recommender System
,
Implicit Trust Metric
,
Context Dependence
References:
References are not available for this document.
Citations
Citations are not available for this document.