LSTM based models stability in the context of Sentiment Analysis for social media

TL;DR

This paper investigates the stability of LSTM-based models in sentiment analysis for social media, analyzing how different configurations affect their robustness and reliability.

Contribution

It introduces an experimental framework to evaluate LSTM model stability and explores the impact of key hyperparameters on performance in sentiment analysis tasks.

Findings

LSTM models show varying stability depending on hyperparameter settings

Certain configurations improve robustness in social media sentiment analysis

The study provides guidelines for stable LSTM model design

Abstract

Deep learning techniques have proven their effectiveness for Sentiment Analysis (SA) related tasks. Recurrent neural networks (RNN), especially Long Short-Term Memory (LSTM) and Bidirectional LSTM, have become a reference for building accurate predictive models. However, the models complexity and the number of hyperparameters to configure raises several questions related to their stability. In this paper, we present various LSTM models and their key parameters, and we perform experiments to test the stability of these models in the context of Sentiment Analysis.