Identifying Avatar Aliases in Starcraft 2

TL;DR

This paper presents a method to identify avatar aliases in Starcraft 2 by analyzing behavioral data and confusion matrices, helping to recognize cyberathletes across different virtual identities.

Contribution

It introduces a novel approach that trains classifiers on behavioral data and processes confusion matrices to detect avatar aliases, addressing a key challenge in e-sports.

Findings

Initial results demonstrate the method's potential effectiveness.

The approach successfully identifies confusing avatar pairs.

Further research is needed for comprehensive validation.

Abstract

In electronic sports, cyberathletes conceal their online training using different avatars (virtual identities), allowing them not being recognized by the opponents they may face in future competitions. In this article, we propose a method to tackle this avatar aliases identification problem. Our method trains a classifier on behavioural data and processes the confusion matrix to output label pairs which concentrate confusion. We experimented with Starcraft 2 and report our first results.