Department of Computer Science and Engineering, Aurora's Technological and Research Institute, Hyderabad 500098, TS, India.
School of Information Technology (SIT), JNTUH, Hyderabad 500085, TS, India.
Comput Intell Neurosci. 2022 May 6;2022:8898100. doi: 10.1155/2022/8898100. eCollection 2022.
Social media is Internet-based by design, allowing people to share content quickly via electronic means. People can openly express their thoughts on social media sites such as Twitter, which can then be shared with other people. During the recent COVID-19 outbreak, public opinion analytics provided useful information for determining the best public health response. At the same time, the dissemination of misinformation, aided by social media and other digital platforms, has proven to be a greater threat to global public health than the virus itself, as the COVID-19 pandemic has shown. The public's feelings on social distancing can be discovered by analysing articulated messages from Twitter. The automated method of recognizing and classifying subjective information in text data is known as sentiment analysis. In this research work, we have proposed to use a combination of preprocessing approaches such as tokenization, filtering, stemming, and building -gram models. Deep belief neural network (DBN) with pseudo labelling is used to classify the tweets. Top layers of the base classifiers are boosted in the pseudo labelling strategy, whereas lower levels of the base classifiers share weights for feature extraction. By introducing the pseudo boost mechanism, our suggested technique preserves the same time complexity as a DBN while achieving fast convergence to optimality. The pseudo labelling improves the performance of the classification. It extracts the keywords from the tweets with high precision. The results reveal that using the DBN classifier in conjunction with the bigram in the -gram model outperformed other models by 90.3 percent. The proposed approach can also aid medical professionals and decision-makers in determining the best course of action for each location based on their views regarding the pandemic.
社交媒体本质上是基于互联网的，允许人们通过电子手段快速共享内容。人们可以在 Twitter 等社交媒体网站上公开表达自己的想法，这些想法随后可以与其他人分享。在最近的 COVID-19 疫情期间，公众意见分析为确定最佳公共卫生应对措施提供了有用信息。与此同时，借助社交媒体和其他数字平台传播的错误信息，已被证明比病毒本身对全球公共卫生构成更大的威胁，正如 COVID-19 大流行所表明的那样。通过分析来自 Twitter 的有表达力的消息，可以发现公众对社交距离的感受。情感分析是一种自动识别和分类文本数据中主观信息的方法。在这项研究工作中，我们提出了使用预处理方法的组合，如标记化、过滤、词干化和构建 -gram 模型。使用伪标签的深度置信神经网络（DBN）对推文进行分类。在伪标签策略中，基分类器的顶层被提升，而基分类器的较低层共享特征提取的权重。通过引入伪提升机制，我们的建议技术在保持与 DBN 相同的时间复杂度的同时，实现了快速收敛到最优。伪标签提高了分类性能。它从推文关键词中提取具有高精度的关键词。结果表明，与其他模型相比，使用 DBN 分类器与 -gram 模型中的二项式结合可将性能提高 90.3%。该方法还可以帮助医疗专业人员和决策者根据他们对大流行的看法，为每个地点确定最佳行动方案。
