Open Access

ARTICLE

A PERT-BiLSTM-Att Model for Online Public Opinion Text Sentiment Analysis

by Mingyong Li, Zheng Jiang^*, Zongwei Zhao, Longfei Ma

College of Computer and Information Science, Chongqing Normal University, Chongqing, 401331, China

* Corresponding Author: Zheng Jiang. Email:

(This article belongs to the Special Issue: Cognitive Granular Computing Methods for Big Data Analysis)

Intelligent Automation & Soft Computing 2023, 37(2), 2387-2406. https://doi.org/10.32604/iasc.2023.037900

Received 20 November 2022; Accepted 10 March 2023; Issue published 21 June 2023

Abstract

As an essential category of public event management and control, sentiment analysis of online public opinion text plays a vital role in public opinion early warning, network rumor management, and netizens’ personality portraits under massive public opinion data. The traditional sentiment analysis model is not sensitive to the location information of words, it is difficult to solve the problem of polysemy, and the learning representation ability of long and short sentences is very different, which leads to the low accuracy of sentiment classification. This paper proposes a sentiment analysis model PERT-BiLSTM-Att for public opinion text based on the pre-training model of the disordered language model, bidirectional long-term and short-term memory network and attention mechanism. The model first uses the PERT model pre-trained from the lexical location information of a large amount of corpus to process the text data and obtain the dynamic feature representation of the text. Then the semantic features are input into BiLSTM to learn context sequence information and enhance the model’s ability to represent long sequences. Finally, the attention mechanism is used to focus on the words that contribute more to the overall emotional tendency to make up for the lack of short text representation ability of the traditional model, and then the classification results are output through the fully connected network. The experimental results show that the classification accuracy of the model on NLPCC14 and weibo_senti_100k public data sets reach 88.56% and 97.05%, respectively, and the accuracy reaches 95.95% on the data set MDC22 composed of Meituan, Dianping and Ctrip comment. It proves that the model has a good effect on sentiment analysis of online public opinion texts on different platforms. The experimental results on different datasets verify the model’s effectiveness in applying sentiment analysis of texts. At the same time, the model has a strong generalization ability and can achieve good results for sentiment analysis of datasets in different fields.

---

Keywords

---