Multichannel Two-Dimensional Convolutional Neural Network Based on Interactive Features and Group Strategy for Chinese Sentiment Analysis

Abstract

In Chinese sentiment analysis tasks, many existing methods tend to use recurrent neural networks (e.g., long short-term memory networks and gated recurrent units) and standard one-dimensional convolutional neural networks (1D-CNN) to extract features. This is because a recurrent neural network can deal with the order dependence of the data to a certain extent and the one-dimensional convolution can extract local features. Although these methods have good performance in sentiment analysis tasks, recurrent neural networks (RNNs) cannot be parallelized, resulting in time-inefficiency, and the standard 1D-CNN can only extract a single sample feature, with the result that the feature information cannot be fully utilized. To this end, in this paper, we propose a multichannel two-dimensional convolutional neural network based on interactive features and group strategy (MCNN-IFGS) for Chinese sentiment analysis. Firstly, we no longer use word encoding technology but use character-based integer encoding to retain more fine-grained information. Besides, in character-level vectors, the interactive features of different elements are introduced to improve the dimensionality of feature vectors and supplement semantic information so that the input matches the model network. In order to ensure that more sentiment features are learned, group strategies are used to form several feature mapping groups, so the learning object is converted from the traditional single sample to the learning of the feature mapping group, so as to achieve the purpose of learning more features. Finally, multichannel two-dimensional convolutional neural networks with different sizes of convolution kernels are used to extract sentiment features of different scales. The experimental results on the Chinese dataset show that our proposed method outperforms other baseline and state-of-the-art methods.

Signal to Image Conversion and Convolutional Neural Networks for Physiological Signal Processing: A Review

“…which must be filtered, denoised and preprocessed. For multichannel data (e.g., multi-lead ECG, high-density EEG/EMG), encoding spatial relationships is important, which cannot be captured in 1D feature vectors [1]. Signals acquired at high sampling rates yield sizable datasets that can strain computational resources, often requiring dimensionality reduction before deploying machine learning models.…”