Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Knowledge-Infusion For Explainable Depression Detection

Sumit Dalal, Sarika Jain, Mayank Dave

TL;DR

A Knolwedge-infused Neural Network (KiNN) incorporating domain-specific knowledge from DepressionFeature ontology in a neural network to endow the model with user-level explainability regarding concepts and processes the clinician understands is proposed.

Abstract

Discovering individuals depression on social media has become increasingly important. Researchers employed ML/DL or lexicon-based methods for automated depression detection. Lexicon based methods, explainable and easy to implement, match words from user posts in a depression dictionary without considering contexts. While the DL models can leverage contextual information, their black-box nature limits their adoption in the domain. Though surrogate models like LIME and SHAP can produce explanations for DL models, the explanations are suitable for the developer and of limited use to the end user. We propose a Knolwedge-infused Neural Network (KiNN) incorporating domain-specific knowledge from DepressionFeature ontology (DFO) in a neural network to endow the model with user-level explainability regarding concepts and processes the clinician understands. Further, commonsense knowledge from the Commonsense Transformer (COMET) trained on ATOMIC is also infused to consider the generic emotional aspects of user posts in depression detection. The model is evaluated on three expertly curated datasets related to depression. We observed the model to have a statistically significant (p<0.1) boost in performance over the best domain-specific model, MentalBERT, across CLEF e-Risk (25% MCC increase, 12% F1 increase). A similar trend is observed across the PRIMATE dataset, where the proposed model performed better than MentalBERT (2.5% MCC increase, 19% F1 increase). The observations confirm the generated explanations to be informative for MHPs compared to post hoc model explanations. Results demonstrated that the user-level explainability of KiNN also surpasses the performance of baseline models and can provide explanations where other baselines fall short. Infusing the domain and commonsense knowledge in KiNN enhances the ability of models like GPT-3.5 to generate application-relevant explanations.

Deep Knowledge-Infusion For Explainable Depression Detection

TL;DR

A Knolwedge-infused Neural Network (KiNN) incorporating domain-specific knowledge from DepressionFeature ontology in a neural network to endow the model with user-level explainability regarding concepts and processes the clinician understands is proposed.

Abstract

Discovering individuals depression on social media has become increasingly important. Researchers employed ML/DL or lexicon-based methods for automated depression detection. Lexicon based methods, explainable and easy to implement, match words from user posts in a depression dictionary without considering contexts. While the DL models can leverage contextual information, their black-box nature limits their adoption in the domain. Though surrogate models like LIME and SHAP can produce explanations for DL models, the explanations are suitable for the developer and of limited use to the end user. We propose a Knolwedge-infused Neural Network (KiNN) incorporating domain-specific knowledge from DepressionFeature ontology (DFO) in a neural network to endow the model with user-level explainability regarding concepts and processes the clinician understands. Further, commonsense knowledge from the Commonsense Transformer (COMET) trained on ATOMIC is also infused to consider the generic emotional aspects of user posts in depression detection. The model is evaluated on three expertly curated datasets related to depression. We observed the model to have a statistically significant (p<0.1) boost in performance over the best domain-specific model, MentalBERT, across CLEF e-Risk (25% MCC increase, 12% F1 increase). A similar trend is observed across the PRIMATE dataset, where the proposed model performed better than MentalBERT (2.5% MCC increase, 19% F1 increase). The observations confirm the generated explanations to be informative for MHPs compared to post hoc model explanations. Results demonstrated that the user-level explainability of KiNN also surpasses the performance of baseline models and can provide explanations where other baselines fall short. Infusing the domain and commonsense knowledge in KiNN enhances the ability of models like GPT-3.5 to generate application-relevant explanations.
Paper Structure (15 sections, 2 figures, 3 tables, 2 algorithms)

This paper contains 15 sections, 2 figures, 3 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Literature
  3. Knowledge-infusion in Depression Detection
  4. Explainable Depression Detection
  5. Knowledge-infused Neural Network (KiNN)
  6. Architecture
  7. Algorithm
  8. Experimental Setup
  9. Datasets
  10. Implementation and Training Details:
  11. Evaluation Metrics:
  12. Results & Discussion
  13. Quantitative Results
  14. User-level Explanations
  15. Conclusion

Figures (2)

  • Figure 1: Comparision of explanations produced by LIME, MentalBERT, Self-Attention, and the proposed KiNN model. The objective is to enhance the ability to provide user-level explanations for depression detection. KiNN highlights variable-length phrases centered around depression, unlike others, which focus on unigrams lacking context for user understand-ability.
  • Figure 2: Knowledge-infused Neural Network (KiNN) model considering different aspects of user posts-domain and commonsense for depression detection. MentalBERT provides context-specific embeddings for phrase-tagged user posts. COMET provides nine aspects related to user posts, five of which are mental-health related and hence considered to check the intent of user posts. KiNN allows visualization of various attention layers for user-level explanations.