Identifying Emotion Labels From Psychiatric Social Texts Using a Bi-Directional LSTM-CNN Model
Open Access
- 2 April 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 66638-66646
Abstract
Discussion features in online communities can be effectively used to diagnose depression and allow other users or experts to provide self-help resources to those in need. Automatic emotion identification models can quickly and effectively highlight indicators of emotional stress in the text of such discussions. Such communities also provide patients with important knowledge to help better understand their condition. This study proposes a deep learning framework combining word embeddings, bi-directional long short-term memory (Bi-LSTM), and convolutional neural networks (CNN) to identify emotion labels from psychiatric social texts. The Bi-LSTM is a powerful mechanism for extracting features from sequential data in which a sentence consists of multiple words in a particular sequence. CNN is another powerful feature extractor which can convolute many blocks to capture important features. Our proposed deep learning framework also applies word representation techniques to represent semantic relationships between words. The paper thus combines two powerful feature extraction methods with word embedding to automatically identify indicators of emotional stress. Experimental results show that our proposed framework outperformed other models using traditional feature extraction such as bag-of-words (BOW), latent semantic analysis (LSA), independent component analysis (ICA), and LSA+ICA.Keywords
Funding Information
- Ministry of Science and Technology (MOST), Taiwan (MOST 107-2628-E-155-002-MY3, MOST 107-2218-E-031 -002 -MY2)
This publication has 44 references indexed in Scilit:
- New term weighting schemes with combination of multiple classifiers for sentiment analysisNeurocomputing, 2015
- Property type distribution in Wordnet, corpora and WikipediaExpert Systems with Applications, 2015
- Large-Scale Multi-label Text Classification — Revisiting Neural Networks2014
- Emotion classification by removal of the overlap from incremental association language featuresJournal of the Chinese Institute of Engineers, 2011
- Multilabel classification via calibrated label rankingMachine Learning, 2008
- Random k-Labelsets: An Ensemble Method for Multilabel Classification2007
- ML-KNN: A lazy learning approach to multi-label learningPattern Recognition, 2007
- LSTM recurrent networks learn simple context-free and context-sensitive languagesIEEE Transactions on Neural Networks, 2001
- Knowledge Discovery in Multi-label Phenotype Data2001
- Virtual Psychiatric ClinicsAmerican Journal of Psychiatry, 2001