A multi domains short message sentiment classification using hybrid neural network architecture

Abstract

Sentiment analysis of short texts is challenging because of its limited context of information. It becomes more challenging to be done on limited resource language like Bahasa Indonesia. However, with various deep learning techniques, it can give pretty good accuracy. This paper explores several deep learning methods, such as multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and builds combinations of those three architectures. The combinations of those three architectures are intended to get the best of those architecture models. The MLP accommodates the use of the previous model to obtain classification output. The CNN layer extracts the word feature vector from text sequences. Subsequently, the LSTM repetitively selects or discards feature sequences based on their context. Those advantages are useful for different domain datasets. The experiments on sentiment analysis of short text in Bahasa Indonesia show that hybrid models can obtain better performance, and the same architecture can be directly used in another domain-specific dataset.

GloVe-CNN-BiLSTM Model for Sentiment Analysis on Text Reviews

“…Ref [8] CNN Ref [9] CNN+RNN+GloVe Ref [10] SDCNN Ref [11] LSTM+GloVe Ref [12] BIGRU+CNN Ref [13] 2D CNN-LSTM Ref [14] Two-channel CNN-LSTM Ref [15] MLP+CNN+LSTM Ref [16] BiLSTM+CNN 3 Journal of Sensors feature items. In practice, word vectorization is often used for semantic feature representation.…”

Sentiment analysis of Twitter posts related to the COVID-19 vaccines

“…They suggested pre-processing the web data to improve the structure of textual data. Others researches used various techniques in sentiment analysis using method of neural network [21], [22], data mining [23], and artificial intelligence [24].…”

Application of multilayer perceptron to deep reinforcement learning for stock market trading and analysis

“…However, the major shortcoming of Q-learning was that, it did not have the ability to estimate value for unseen states [36]. Other learning methods like recurrent reinforcement network (RRN) and LSTM [37], [38] did not provide better improvements either. Studies have shown that the ability of Q-learning can be enhanced, by incorporating DRL techniques, to attain improved predictive results as output of an experiment [39].…”