The Ties that matter: From the perspective of Similarity Measure in Online Social Networks

TL;DR

This paper introduces NDES, an asymmetric similarity measure for social networks that considers connection density and directionality, improving community detection accuracy.

Contribution

The paper proposes NDES, a novel asymmetric similarity measure that accounts for density and directionality, enhancing community detection in social networks.

Findings

NDES outperforms existing similarity measures in community detection accuracy.

Empirical results demonstrate improved community quality with NDES.

NDES has a computational complexity of O(nk^2).

Abstract

Online Social Networks have embarked on the importance of connection strength measures which has a broad array of applications such as, analyzing diffusion behaviors, community detection, link predictions, recommender systems. Though there are some existing connection strength measures, the density that a connection shares with it's neighbors and the directionality aspect has not received much attention. In this paper, we have proposed an asymmetric edge similarity measure namely, Neighborhood Density-based Edge Similarity (NDES) which provides a fundamental support to derive the strength of connection. The time complexity of NDES is $O(nk^2)$. An application of NDES for community detection in social network is shown. We have considered a similarity based community detection technique and substituted its similarity measure with NDES. The performance of NDES is evaluated on several small real-world datasets in terms of the effectiveness in detecting communities and compared with three widely used similarity measures. Empirical results show NDES enables detecting comparatively better communities both in terms of accuracy and quality.