Leveraging deep graph-based text representation for sentiment polarity applications

作者：

Highlights：

• highlights

• Employ a graph based representation to extract semantics of textual data.

• Propose a probabilistic feature learning approach on graph representation.

• Apply deep learning architectures on sentiment classification.

• Experimental results are performed on benchmark datasets.

• The results show that the proposed approach outperformed the earlier methods.

摘要

highlights•Employ a graph based representation to extract semantics of textual data.•Propose a probabilistic feature learning approach on graph representation.•Apply deep learning architectures on sentiment classification.•Experimental results are performed on benchmark datasets.•The results show that the proposed approach outperformed the earlier methods.

论文关键词：Sentiment analysis,Graph representation,Representation learning,Feature learning,Deep neural networks

论文评审过程：Received 20 January 2019, Revised 17 October 2019, Accepted 15 November 2019, Available online 15 November 2019, Version of Record 21 November 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.113090