This paper provides a comprehensive review of over 150 deep learning (DL) models for text classification, including sentiment analysis, news categorization, question answering, and natural language inference. The authors discuss the technical contributions, similarities, and strengths of these models, and provide a summary of more than 40 popular datasets used in text classification. They also present a quantitative analysis of the performance of selected DL models on 16 popular benchmarks and discuss future research directions. The paper is structured into several sections, covering various types of models such as feed-forward networks, RNNs, CNNs, attention mechanisms, memory-augmented networks, graph neural networks, Siamese neural networks, and hybrid models. Each section reviews specific models and their architectures, highlighting their advantages and applications. The paper concludes by discussing the challenges and future directions in DL-based text classification.This paper provides a comprehensive review of over 150 deep learning (DL) models for text classification, including sentiment analysis, news categorization, question answering, and natural language inference. The authors discuss the technical contributions, similarities, and strengths of these models, and provide a summary of more than 40 popular datasets used in text classification. They also present a quantitative analysis of the performance of selected DL models on 16 popular benchmarks and discuss future research directions. The paper is structured into several sections, covering various types of models such as feed-forward networks, RNNs, CNNs, attention mechanisms, memory-augmented networks, graph neural networks, Siamese neural networks, and hybrid models. Each section reviews specific models and their architectures, highlighting their advantages and applications. The paper concludes by discussing the challenges and future directions in DL-based text classification.