Seating Assignment Using Constrained Signed Spectral Clustering

TL;DR

This paper introduces a constrained signed spectral clustering method for seating assignments that optimizes social affinity and minimizes discomfort by considering cluster size constraints.

Contribution

It extends signed spectral clustering to incorporate cluster size constraints, enabling more practical grouping solutions in social scenarios.

Findings

Effective grouping of socially compatible individuals

Reduces awkward interactions in seating arrangements

Demonstrates efficiency in real-world scenarios

Abstract

In this paper, we present a novel method for constrained cluster size signed spectral clustering which allows us to subdivide large groups of people based on their relationships. In general, signed clustering only requires K hard clusters and does not constrain the cluster sizes. We extend signed clustering to include cluster size constraints. Using an example of seating assignment, we efficiently find groups of people with high social affinity while mitigating awkward social interaction between people who dislike each other.