Back to all available

HEAL-MinD: Hybrid contextual and semantic embeddings with attention and linguistic features for mental health detection

artificial-intelligence
data-mining-and-machine-learning
data-science
social-computing
text-mining

Abstract

The occurrences of events like data breaches, loss of sensitive information, and inappropriate use of an individual's personal information often adversely impact the mental health of users. It can be extensively seen in users' online posts across varied social media platforms and other online sources after the occurrences of such events. It reflects a range of emotions, ranging from frustration, depression, anxiety, stress, sadness, to a sense of mistrust. Analyzing these online complaint-based posts shows valuable insights into the mental health challenges of users, especially when it is related to privacy concerns, financial loss, or reputational damage. In this paper, we present a novel deep learning model called HEAL-MinD to detect mental health based on online user posts. It begins with an input layer that processes the input text. The subsequent embedding layer utilizes two types of embeddings to transform the input text into numerically enriched representations that capture both contextual and semantic information. A CGAT layer is introduced, and it is one of the most important components of HEAL-MinD. It learns the syntactic, semantic, and contextual representations in parallel and opposite directions and also emphasizes important mental health-related words in the text. In addition, a hand-crafted rich set of auxiliary features is also incorporated into the model. It consists of 23 linguistic and mental health-related lexical features via generating a new lexicon. It helps in supporting our model to be more accurate and informed. Finally, a dense layer carries out the final classification, and the output layer produces the result, categorizing each input as either mental health or non-mental health. We conduct experimental evaluations on three newly developed datasets to demonstrate the effectiveness of the HEAL-MinD model. It outperforms the 5 existing studies and 12 baseline models and achieves an f-score and accuracy of up to 95 and 96, respectively, across three datasets. The required source code to implement the HEAL-MinD model is available at GitHub: https://github.com/vishxl/HEAL-MinD
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].