TextConvoNet: a convolutional neural network based architecture for text classification

Abstract

This paper presents, TextConvoNet , a novel Convolutional Neural Network (CNN) based architecture for binary and multi-class text classification problems. Most of the existing CNN-based models use one-dimensional convolving filters, where each filter specializes in extracting n-grams features of a particular input word embeddings (Sentence Matrix). These features can be termed as intra-sentence n-gram features. To the best of our knowledge, all the existing CNN models for text classification are based on the aforementioned concept. The presented TextConvoNet not only extracts the intra-sentence n-gram features but also captures the inter-sentence n-gram features in input text data. It uses an alternative approach for input matrix representation and applies a two-dimensional multi-scale convolutional operation on the input. We perform an experimental study on five binary and multi-class classification datasets and evaluate the performance of the TextConvoNet for text classification. The results are evaluated using eight performance measures, accuracy, precision, recall, f1-score, specificity, gmean1, gmean2, and Mathews correlation coefficient (MCC). Furthermore, we extensively compared presented TextConvoNet with machine learning, deep learning, and attention-based models. The experimental results evidenced that the presented TextConvoNet outperformed and yielded better performance than the other used models for text classification purposes.

Imbalanced Text Sentiment Classification Based on Multi-Channel BLTCN-BLSTM Self-Attention

“…(2) TextCNN [ 14 ]: The word embedding settings were unchanged; only the TextCNN single-channel model was used, L-Softmax enhancement was not added, and Focal Loss was rebalanced.…”

“…The excellent performance of most methods is based on the assumption that the samples between classes in the dataset are balanced [ 11 , 12 , 13 ]. For example, Irsoy et al [ 11 ] applied RNN for text sentiment orientation classification, Kim et al [ 12 ] used CNN for text sentiment orientation classification, and Soni et al [ 14 ] proposed TextConvoNet, a novel convolutional neural network (CNN)-based architecture for solving binary and multi-class text classification problems. At the same time, some scholars have begun to study the classification problem based on imbalanced data [ 15 , 16 ].…”

Deep learning-based application for multilevel sentiment analysis of Indonesian hotel reviews

“…Implementing a neural network with multiple hidden layers provides a high feature learning capability, which is beneficial for visualizing or classifying data [ 31 ]. Convolutional Neural Network (CNN) as a form of deep learning architecture also has the same advantage, i.e., the trained CNN-based model for text classification can recognize patterns in text automatically, such as key phrases [ 32 ]. To extract a feature vector from the input word embeddings, CNN-based models employ one-dimensional (1-D) convolution followed by a one-dimensional pooling operation (average or max).…”

ERNIE and Multi-Feature Fusion for News Topic Classification

“…The literature by Dogru et al (2021) proposes a news classification method based on doc2vec and convolutional neural network (CNN). The feature vectors of news text are obtained by Doc2vec, and the text features are further extracted by CNN (Soni et al, 2023). The literature by Agarwal et al (2023) proposes a news classifier based on machine learning algorithms.…”