Racism Detection by Analyzing Differential Opinions Through Sentiment Analysis of Tweets Using Stacked Ensemble GCR-NN Model
Racism Detection by Analyzing Differential Opinions Through Sentiment Analysis of Tweets Using Stacked Ensemble GCR-NN Model
复制标题
DOI：
10.1109/access.2022.3144266
复制
发表时间：
2022-01-01
期刊：
影响因子：
3.9
通讯作者：
Ashraf, Imran
中科院分区：
文献类型：
--
作者：
Lee, Ernesto;Rustam, Furqan;Ashraf, Imran
随着社交媒体在社会政治领域的主导作用，社交媒体上出现了几种现有和新形式的种族主义。种族主义以不同的形式出现在社交媒体上，有隐藏的，也有公开的，隐藏的是使用模因，公开的是使用假身份煽动仇恨，暴力和社会不稳定的种族主义言论。虽然种族主义通常与种族有关，但现在种族主义基于肤色，起源，语言，文化，最重要的是宗教而蓬勃发展。煽动种族差异的社交媒体观点和言论被视为对社会、政治和文化稳定的严重威胁，并威胁到不同国家的和平。因此，应监测作为种族主义言论传播主要来源的社交媒体，并及时发现和阻止种族主义言论。本研究的目的是通过对推文进行情感分析来检测包含种族主义文本的推文。由于深度学习的上级性能，通过组合门控递归单元（GRU）、卷积神经网络（CNN）和递归神经网络RNN（称为门控卷积递归神经网络（GCR-NN））来组装堆叠集成深度学习模型。GRU在GCR-NN模型中处于领先地位，从原始文本中提取合适的突出特征，CNN提取重要特征，以便RNN做出准确的预测。显然，在机器学习和深度学习模型的范围内进行了几个实验来研究和分析所提出的GCR-NN的性能，表明GCR-NN的上级性能提高了0.98的准确度。建议的GCR-NN模型可以检测到97%的包含种族主义评论的推文。
With social media's dominating role in the socio-political landscape, several existing and new forms of racism took place on social media. Racism has emerged on social media in different forms, both hidden and open, hidden with the use of memes and open as the racist remarks using fake identities to incite hatred, violence, and social instability. Although often associated with ethnicity, racism is now thriving based on color, origin, language, cultures, and most importantly religion. Social media opinions and remarks provocating racial differences have been regarded as a serious threat to social, political, and cultural stability and have threatened the peace of different countries. Consequently, social media being the leading source of racist opinions dissemination should be monitored and racism remarks should be detected and blocked timely. This study aims at detecting Tweets that contain racist text by performing the sentiment analysis of Tweets. Owing to the superior performance of deep learning, a stacked ensemble deep learning model is assembled by combining gated recurrent unit (GRU), convolutional neural networks (CNN), and recurrent neural networks RNN, called, Gated Convolutional Recurrent- Neural Networks (GCR-NN). GRU is on the top in the GCR-NN model to extract the suitable and prominent features from raw text, CNN extracts important features for RNN to make accurate predictions. Obviously, several experiments are conducted to investigate and analyze the performance of the proposed GCR-NN within the scope of machine learning and deep learning models indicating the superior performance of GCR-NN with increased 0.98 accuracy. The proposed GCR-NN model can detect 97% of the tweets that contain racist comments.