Deep Learning Sentiment Classification Based on Weak Tagging Information

Abstract

The purpose of sentiment classification is to solve the problem of automatic judgment of text sentiment tendency. In the sentiment classification task of online reviews, traditional deep learning sentiment classification models focus on algorithm optimization to improve the classification performance of the model, but when the sample data for manually labeling sentiment tendencies is insufficient, the classification performance of the model will be poor. The deep learning sentiment classification model based on weak tagging information, on the one hand, introduces weak tagging information into the training process of the model to reduce the use of manually tagging data. On the other hand, weak tagging information can represent the sentiment tendency of reviews to a certain extent, but it also contains noise, the model reduces the negative impact of the noise in weak tagging information in order to improve the classification performance of the sentiment classification model. The experimental results show that in the sentiment classification task of hotel online reviews, the deep learning sentiment classification model based on weak tagging information has superior classification performance than the traditional deep model without increasing labor cost.

Survey on sentiment analysis: evolution of research methods and topics

“…There is a keyword named "performance sentiment" in the C4 community. Precision, recall, accuracy and F1-score are the most commonly used evaluation metrics (Dangi et al 2022;Jain et al 2022;JayaLakshmi and Kishore 2022;Li et al 2017;Wang et al 2021;Yi and Niblack 2005). Some researchers have also used runtimes to calculate the model efficiency (Abo et al 2021;Ferilli et al 2015), p-value to statistically evaluate the relationship or difference between two samples of classification results (JayaLakshmi and Kishore 2022; Salur and Aydin 2020), paired sample t-tests to verify that the results are not obtained by chance (Nhlabano and Lutu 2018)…”

Bio-Inspired Artificial Intelligence with Natural Language Processing Based on Deceptive Content Detection in Social Networking

“…LSTM-NN is a kind of RNN that presents a 'gate' model. It is capable of capturing the long-term semantic dependence and preventing the gradient-disappearing problems of the classical RNN, due to its long sequence [24]. Thus, the LSTM approach is applied for sentiment classification tasks.…”

Artificial Intelligence Technology-Based Semantic Sentiment Analysis on Network Public Opinion Texts

“…However, it has few applicable fields and does not provide a comprehensive method for sentiment analysis. Wang et al (2021) proposed a D-L model with weak labeling as a solution to the poor performance of traditional models. This method reduced the negative impact of noise on weakly labeled information, but did not enable users to reach convergence in less time.…”