PDF(Sci-hub)
Abstract：
The widespread use of social media provides a large amount of data for public sentimentanalysis. Based on social media data, researchers can study public opinions on humanpapillomavirus (HPV) vaccines on social media using machine learning-based approaches that willhelp us understand the reasons behind the low vaccine coverage. However, social media data isusually unannotated, and data annotation is costly. The lack of an abundant annotated dataset limitsthe application of deep learning methods in effectively training models. To tackle this problem, wepropose three transfer learning approaches to analyze the public sentiment on HPV vaccines onTwitter. One was transferring static embeddings and embeddings from language models (ELMo)and then processing by bidirectional gated recurrent unit with attention (BiGRU-Att), called DWEBiGRU-Att. The others were fine-tuning pre-trained models with limited annotated data, called finetuninggenerative pre-training (GPT) and fine-tuning bidirectional encoder representations fromtransformers (BERT). The fine-tuned GPT model was built on the pre-trained generative pretraining(GPT) model. The fine-tuned BERT model was constructed with BERT model. Theexperimental results on the HPV dataset demonstrated the efficacy of the three methods in thesentiment analysis of the HPV vaccination task. The experimental results on the HPV datasetdemonstrated the efficacy of the methods in the sentiment analysis of the HPV vaccination task. Thefine-tuned BERT model outperforms all other methods. It can help to find strategies to improvevaccine uptake.
摘要：
社交媒体的广泛使用为公众情绪分析提供了大量数据。基于社交媒体数据,研究人员可以使用基于机器学习的方法在社交媒体上研究关于人乳头瘤病毒(HPV)疫苗的公众意见,这将有助于我们了解疫苗覆盖率低背后的原因.然而,社交媒体数据通常没有注释，而且数据注释成本很高。缺乏丰富的注释数据集限制了深度学习方法在有效训练模型中的应用。为了解决这个问题，我们提出了三种迁移学习方法来分析Twitter上关于HPV疫苗的公众情绪。一种是从语言模型（ELMo）转移静态嵌入和嵌入，然后通过双向门控循环单元（BiGRU-Att）进行处理，叫做DWEBIGRU-Att。其他的是用有限的注释数据微调预训练模型，称为精细训练生成预训练（GPT）和来自变压器（BERT）的微调双向编码器表示。微调GPT模型建立在预训练生成预训练(GPT)模型上。利用BERT模型构建了微调BERT模型。HPV数据集上的实验结果证明了三种方法在HPV疫苗接种任务的情感分析中的有效性。HPV数据上的实验结果证明了这些方法在HPV疫苗接种任务的情感分析中的有效性。经过efine调整的BERT模型优于所有其他方法。它可以帮助找到改善疫苗摄取的策略。
