Fuzzy-Rough Nearest Neighbour Approaches for Emotion Detection in Tweets

TL;DR

This paper introduces a fuzzy rough nearest neighbour approach with ensemble techniques for emotion detection in tweets, achieving competitive results with complex deep learning models in the SemEval-2018 task.

Contribution

It presents a novel fuzzy rough set-based classification method combined with ensemble learning and text embeddings for emotion detection in social media data.

Findings

Competitive performance with deep learning methods

Effective use of fuzzy rough sets for textual emotion recognition

Ensemble of FRNN-OWA models improves accuracy

Abstract

Social media are an essential source of meaningful data that can be used in different tasks such as sentiment analysis and emotion recognition. Mostly, these tasks are solved with deep learning methods. Due to the fuzzy nature of textual data, we consider using classification methods based on fuzzy rough sets. Specifically, we develop an approach for the SemEval-2018 emotion detection task, based on the fuzzy rough nearest neighbour (FRNN) classifier enhanced with ordered weighted average (OWA) operators. We use tuned ensembles of FRNN--OWA models based on different text embedding methods. Our results are competitive with the best SemEval solutions based on more complicated deep learning methods.