QMUL-SDS @ SardiStance: Leveraging Network Interactions to Boost Performance on Stance Detection using Knowledge Graphs

TL;DR

This paper describes a stance detection approach leveraging social interaction features and knowledge graphs, achieving competitive results in shared tasks by enhancing neural models with social context.

Contribution

The paper introduces a method that incorporates social interaction features and knowledge graphs to improve stance detection performance.

Findings

Social interaction features significantly boost model accuracy.

Knowledge graphs contribute to better understanding of stance.

Model achieved 6th place in shared task with improved settings.

Abstract

This paper presents our submission to the SardiStance 2020 shared task, describing the architecture used for Task A and Task B. While our submission for Task A did not exceed the baseline, retraining our model using all the training tweets, showed promising results leading to (f-avg 0.601) using bidirectional LSTM with BERT multilingual embedding for Task A. For our submission for Task B, we ranked 6th (f-avg 0.709). With further investigation, our best experimented settings increased performance from (f-avg 0.573) to (f-avg 0.733) with same architecture and parameter settings and after only incorporating social interaction features -- highlighting the impact of social interaction on the model's performance.