Negative emotions detection on online mental-health related patients texts using the deep learning with MHA-BCNN model

作者：

Highlights：

• Detecting mental health emotions from online patients texts.

• Identifying both the negative emotions and the multi-labeled classification.

• Using Deep Learning with word-embeddings to capture emotions from text sequence.

• Proposed a MHA-BiLSTM with CNN model to enhance the long-term dependencies.

• Our results show that our model performs better than the earlier research works.

摘要

•Detecting mental health emotions from online patients texts.•Identifying both the negative emotions and the multi-labeled classification.•Using Deep Learning with word-embeddings to capture emotions from text sequence.•Proposed a MHA-BiLSTM with CNN model to enhance the long-term dependencies.•Our results show that our model performs better than the earlier research works.

论文关键词：Emotion analysis,Mental-health-care,GloVe-embeddings,Deep learning,MHA-BCNN

论文评审过程：Received 15 March 2021, Revised 19 May 2021, Accepted 20 May 2021, Available online 30 May 2021, Version of Record 8 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115265