Systematic Review of Sentiment Analysis: Insights Through CNN-LSTM Networks

Sentiment analysis, leveraging advancements in Natural Language Processing (NLP) and Machine Learning (ML), has become a pivotal tool for interpreting public opinion in various sectors. This systematic review delves into the innovative integration of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks within this field, with a particular focus on customer evaluations in the digital age. While traditional sentiment analysis primarily utilized classical ML and lexicon-based methods, the incorporation of deep learning (DL) techniques has marked a transformative phase, especially in analyzing extensive social network data. Our review guides readers through the DL landscape in sentiment analysis, highlighting the combined strengths of CNN and LSTM models. It offers an in-depth examination of various sentiment analysis methodologies, underscoring the profound impact of CNN-LSTM networks. This paper discusses diverse sentiment analysis approaches, their practical applications, and addresses the challenges faced. Notably, the synergy of CNN and LSTM has led to significant advancements in interpreting complex sentiment data, opening new avenues in marketing, brand management, and public opinion analysis. The goal of this review is to provide an extensive understanding of DL in sentiment analysis, shedding light on its contemporary applications and potential future developments.