A Hybrid Semantic-Topic Co-encoding Network for Social Emotion Classification

Dai, Lu; Wang, Bang; Xiang, Wei; Xu, Minghua; Han, Xu

doi:10.1007/978-3-031-05933-9_46

Cited by 4 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yadav and Vishwakarma [63] presented a deep language-independent Multilevel Attention-based Conv-BiGRU network (MACBiG-Net), that employs both embedding and attention mechanisms at sentence-level and word-level to extract the sentiments. Dai et al [13] presented a hybrid semantic-topic co-encoding network with a semantics-driven topic encoder to combine topic embeddings and a forward self-attention network to classify social emotions based on their semantics. Zulqarnain et al [70] have designed Two State Gated Recurrent Units (TS-GRU) with feature attention mechanisms to identify and categorize sentiment polarity using word-feature seizing.…”

Section: Related Workmentioning

confidence: 99%

Enhanced sentiment analysis regarding COVID-19 news from global channels

et al. 2022

Self Cite

View full text Add to dashboard Cite

For a healthy society to exist, it is crucial for the media to focus on disease-related issues so that more people are widely aware of them and reduce health risks. Recently, deep neural networks have become a popular tool for textual sentiment analysis, which can provide valuable insights and real-time monitoring and analysis regarding health issues. In this paper, as part of an effort to develop an effective model that can elicit public sentiment on COVID-19 news, we propose a novel approach Cov-Att-BiLSTM for sentiment analysis of COVID-19 news headlines using deep neural networks. We integrate attention mechanisms, embedding techniques, and semantic level data labeling into the prediction process to enhance the accuracy. To evaluate the proposed approach, we compared it to several deep and machine learning classifiers using various metrics of categorization efficiency and prediction quality, and the experimental results demonstrate its superiority with 0.931 testing accuracy. Furthermore, 73,138 pandemic-related tweets posted on six global channels were analyzed by the proposed approach, which accurately reflects global coverage of COVID-19 news and vaccination.

show abstract

Section: Related Workmentioning

confidence: 99%