mlsanityData to 7 Oct 2026

Topic Modeling Based Multi-modal Depression Detection

arXiv 1803.10384 ↗First posted 28 Mar 2018cs.CL cs.IR cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

Major depressive disorder is a common mental disorder that affects almost 7% of the adult U.S. population. The 2017 Audio/Visual Emotion Challenge (AVEC) asks participants to build a model to predict depression levels based on the audio, video, and text of an interview ranging between 7-33 minutes. Since averaging features over the entire interview will lose most temporal information, how to discover, capture, and preserve useful temporal details for such a long interview are significant challenges. Therefore, we propose a novel topic modeling based approach to perform context-aware analysis of the recording. Our experiments show that the proposed approach outperforms context-unaware methods and the challenge baselines for all metrics.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 4; 2024: 9; 2025: 7; 2026: 3.

29 papers.

Sort:

By area:

  1. 2022Automatic Depression Detection: An Emotional Audio-Textual Corpus and a GRU/BiLSTM-based Modelcited by 37
  2. 2023Self-supervised representations in speech-based depression detectioncited by 18
  3. 2024When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detectioncited by 16
  4. 2022Multi-modal Depression Estimation based on Sub-attentional Fusioncited by 15
  5. 2024Synthetic Data Generation with LLM for Improved Depression Predictioncited by 13
  6. 2024HiQuE: Hierarchical Question Embedding Network for Multimodal Depression Detectioncited by 12
  7. 2025U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detectioncited by 12
  8. 2021Two-stage Temporal Modelling Framework for Video-based Depression Recognition using Graph Representationcited by 10
  9. 2023Affect Recognition in Conversations Using Large Language Modelscited by 9
  10. 2024MoodCapture: Depression Detection Using In-the-Wild Smartphone Imagescited by 8
  11. 2022Automatic Depression Detection via Learning and Fusing Features from Visual Cuescited by 5
  12. 2024Context-Aware Deep Learning for Multi Modal Depression Detectioncited by 4
17 more
  1. 2022Neural Architecture Searching for Facial Attributes-based Depression Recognitioncited by 2
  2. 2023Discovering Mental Health Research Topics with Topic Modelingcited by 2
  3. 2024Confidence Estimation for Automatic Detection of Depression and Alzheimer's Disease Based on Clinical Interviewscited by 2
  4. 2025Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaborationcited by 2
  5. 2022Integration of Text and Graph-based Features for Detecting Mental Health Disorders from Voicecited by 1
  6. 2023Cost-effective Models for Detecting Depression from Speechcited by 1
  7. 2024CANAMRF: An Attention-Based Model for Multimodal Depression Detectioncited by 1
  8. 2024A BERT-Based Summarization approach for depression detectioncited by 1
  9. 2024Improving Speech-based Emotion Recognition with Contextual Utterance Analysis and LLMscited by 1
  10. 2025Explainable Multimodal Depression Recognition in Clinical Interviews via PHQ-Aligned Symptom Summarizationcited by 1
  11. 2025Uncertainty Modeling in Multimodal Speech Analysis Across the Psychosis Spectrumcited by 1
  12. 2025Automatic Depression Assessment using Machine Learning: A Comprehensive Surveycited by 1
  13. 2025Probabilistic Textual Time Series Depression Detectioncited by 1
  14. 2026Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoningcited by 1
  15. 2025Enhancing BERTopic with Intermediate Layer Representationscited by 0
  16. 2026Can Conversational Temporal Dynamics Improve Depression Detection in Dyads? A Preliminary Investigation in Multi-Modality Perspectivescited by 0
  17. 2026DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimizationcited by 0