NIHRIO at SemEval-2018 Task 3: A Simple and Accurate Neural Network Model for Irony Detection in Twitter

TL;DR

This paper presents NIHRIO, a straightforward neural network approach utilizing diverse linguistic features for effective irony detection in Twitter, achieving top-tier results in SemEval-2018.

Contribution

Introduces a simple neural network model with multiple feature types for irony detection, demonstrating competitive performance in a challenging social media task.

Findings

Ranked third in accuracy among participants

Achieved fifth place in F1 score

Effective use of lexical, syntactic, semantic, and polarity features

Abstract

This paper describes our NIHRIO system for SemEval-2018 Task 3 "Irony detection in English tweets". We propose to use a simple neural network architecture of Multilayer Perceptron with various types of input features including: lexical, syntactic, semantic and polarity features. Our system achieves very high performance in both subtasks of binary and multi-class irony detection in tweets. In particular, we rank third using the accuracy metric and fifth using the F1 metric. Our code is available at https://github.com/NIHRIO/IronyDetectionInTwitter