Deep Learning for Suicide and Depression Identification with Unsupervised Label Correction

Haque, Ayaan; Reddi, Venkata Senthil Kumar; Giallanza, Tyler

doi:10.1007/978-3-030-86383-8_35

Cited by 20 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are three files in this dataset: the crawled corpus, the SDCNL training corpus and the SDCNL testing corpus. "CAMS" contains annotated SDCNL dataset [5] for causal categorization to test the robustness of the proposed experts guidelines.…”

Section: Datasetmentioning

confidence: 99%

Causal Categorization of Mental Health Posts using Transformers

Kaur

Bhardwaj

Jain

et al. 2022

Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation

View full text Add to dashboard Cite

With recent developments in digitization of clinical psychology, NLP research community has revolutionized the field of mental health detection on social media. Existing research in mental health analysis revolves around the cross-sectional studies to classify users' intent on social media. For in-depth analysis, we investigate existing classifiers to solve the problem of causal categorization which suggests the inefficiency of learning based methods due to limited training samples. To handle this challenge, we use transformer models and demonstrate the efficacy of a pre-trained transfer learning on "CAMS" dataset [4]. The experimental result improves the accuracy and depicts the importance of identifying cause-and-effect relationships in the underlying text.

show abstract

Section: Datasetmentioning

confidence: 99%

Causal Categorization of Mental Health Posts using Transformers

Kaur

Bhardwaj

Jain

et al. 2022

Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation

View full text Add to dashboard Cite

show abstract

“…According to Psychiatry, depression is defined as a mental condition characterized by severe despondency and dejection, typically also with feelings of inadequacy and guilt, often accompanied by lack of energy and disturbance of appetite and sleep. Depression remains a significant issue worldwide, and often it progresses to suicidal intention if left undetected (Haque et al, 2021). Thus the diagnosis of depression is an important task.…”

Section: Introductionmentioning

confidence: 99%

“…We can scrape these resources to create datasets. Such data, if annotated, can be helpful to detect depression (Haque et al, 2021). A growing number of studies are using such data for research and diagnostic purposes.…”

Section: Introductionmentioning

confidence: 99%

DepressionOne@LT-EDI-ACL2022: Using Machine Learning with SMOTE and Random UnderSampling to Detect Signs of Depression on Social Media Text.

Dowlagar¹,

Mamidi²

2022

Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion

View full text Add to dashboard Cite

Depression is a common and serious medical illness that negatively affects how you feel, the way you think, and how you act. Detecting depression is essential as it must be treated early to avoid painful consequences. Nowadays, people are broadcasting how they feel via posts and comments. Using social media, we can extract many comments related to depression and use NLP techniques to train and detect depression. This work presents the submission of the DepressionOne team at LT-EDI-2022 for the shared task, detecting signs of depression from social media text. The depression data is small and unbalanced. Thus, we have used oversampling and undersampling methods such as SMOTE and RandomUnderSampler to represent the data. Later, we used machine learning methods to train and detect the signs of depression.

show abstract