Automated Text-based Depression Detection using Hybrid ConvLSTM and Bi-LSTM Model

Firoz, Neda; Beresteneva, Olga Grigorievna; Vladimirovich, Aksyonov Sergey; Tahsin, Mohammad Sadman; Tafannum, Faiza

doi:10.1109/icais56108.2023.10073683

Cited by 11 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hybrid model of CNN-LSTM-Bi-LSTM acquired an accuracy of 81% with 25 epochs in the work [24], which used DAIC-WOZ dataset. Some other cutting-edge models like LSTM, CNN-LSTM, CNN-Bi-LSTM were also used in this paper and performed well also but not like the proposed hybrid model.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Depression Detection through Advanced Text Analysis: Integrating BERT, Autoencoder, and LSTM Models

Firoz

Beresteneva

Vladimirovich

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Depression is a austere medical ailment that upsets numerous people worldwide, causing a persistent decrease in mood and significantly impacting their emotions. The article focuses on utilizing BERT techniques and Autoencoders to detect depression from text data, considering gender differences. The work stresses on feature engineering of text data provided by benchmark dataset DAIC_WOZ. We experiment with BERT embeddings that encodes the meaning of text to derive text features. They are then fused with the help of Autoencoders with other parametric features from PHQ-8 survey responses, absolutist word count and gender information. The study found that incorporating this information significantly enhances the functioning of the model. The proposed method outperformed the baseline models. We emphasize the potential of machine learning for mental health research that considers gender differences. We report 98.6% accuracy demonstrated by our method. We found the mean absolute error (MAE) as 0.19 and root mean squared error (RMSE) as 0.282 which signifies the high performance of our proposed method for binary depression classification.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing Depression Detection through Advanced Text Analysis: Integrating BERT, Autoencoder, and LSTM Models

Firoz

Beresteneva

Vladimirovich

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Highest Accuracy Based Automated Depression Prediction Using Natural Language Processing

Tharun,

Saranya,

Tamilvizhi

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Review and content analysis of textual expressions as a marker for depressive and anxiety disorders (DAD) detection using machine learning

Sharma,

Damani,

Chariar

2023

Discov Artif Intell

View full text Add to dashboard Cite

Depressive disorders (including major depressive disorder and dysthymia) and anxiety (generalized anxiety disorder or GAD) disorders are the two most prevalent mental illnesses. Early diagnosis of these afflictions can lead to cost-effective treatment with a better outcome prospectus. With the advent of digital technology and platforms, people express themselves by various means, such as social media posts, blogs, journals, instant messaging services, etc. Text remains the most common and convenient form of expression. Therefore, it can be used to predict the onset of anxiety and depression. Scopus and Web of Science (WoS) databases were used to retrieve the relevant literature using a set of predefined search strings. Irrelevant publications were filtered using multiple criteria. The research meta data was subsequently analyzed using the Biblioshiny Tool of R. Finally, a comparative analysis of most suitable documents is presented. A total of 103 documents were used for bibliometric mapping in terms of research outcome over the past years, productivity of authors, institutions, and countries, collaborations, trend topics, keyword co-occurrence, etc. Neural networks and support vector machines are the most popular ML techniques; word embeddings are extensively used for text representations. There is a shift toward using multiple modalities. SVM, Naive Bayes, and LSTM are the most used ML methods; social media is the most used source of data (Twitter is the most common platform); and audio is the most used modality that is combined with text for depressive and anxiety disorders (DAD) detection. Text data provides good cues for the detection of DAD using machine learning. However, the findings in most of the cases are based on a limited amount of data. Using large amounts of data with other modalities can help develop more generalized DAD-detection systems. Asian countries are leading in the research output with China and India being the top countries in terms of the number of research publications. However, more international collaborations are needed. Limited research exists for anxiety disorders. Co-occurrence of anxiety and depressive disorders is high (33% of studies).

show abstract

Automated Text-based Depression Detection using Hybrid ConvLSTM and Bi-LSTM Model

Cited by 11 publications

References 19 publications

Enhancing Depression Detection through Advanced Text Analysis: Integrating BERT, Autoencoder, and LSTM Models

Enhancing Depression Detection through Advanced Text Analysis: Integrating BERT, Autoencoder, and LSTM Models

Highest Accuracy Based Automated Depression Prediction Using Natural Language Processing

Review and content analysis of textual expressions as a marker for depressive and anxiety disorders (DAD) detection using machine learning

Contact Info

Product

Resources

About