LSTM based models stability in the context of Sentiment Analysis for social media
This work addresses stability issues in deep learning models for sentiment analysis, which is important for researchers and practitioners in NLP, but it is incremental as it focuses on testing existing methods rather than introducing new ones.
The paper investigates the stability of LSTM-based models for sentiment analysis on social media, finding that model complexity and hyperparameter tuning impact performance, with results showing variations in accuracy and robustness across different configurations.
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.