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

Bousselham El Haddaoui; Raddouane Chiheb; Rdouan Faizi; Abdellatif El Afia

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

Machine Learning 2022-11-22 v1 Computation and Language Information Retrieval

Authors: Bousselham El Haddaoui , Raddouane Chiheb , Rdouan Faizi , Abdellatif El Afia

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.

Keywords

sentiment analysis long short-term memory recurrent neural networks model stability social media hyperparameters

Cite

@article{arxiv.2211.11246,
  title  = {LSTM based models stability in the context of Sentiment Analysis for social media},
  author = {Bousselham El Haddaoui and Raddouane Chiheb and Rdouan Faizi and Abdellatif El Afia},
  journal= {arXiv preprint arXiv:2211.11246},
  year   = {2022}
}

Comments

Short note, 3 pages, MoroccoAI Annual Conference 2021

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

Abstract

Keywords

Cite

Comments

Related papers