Disentangling the Interpretive and Predictive Roles of LIWC: Controlled Substitution in Depression-Related Classification

2026/07/24 by Hsiang-Chen Yeh, Xiutian Zhao, Aurosweta Mahapatra +3
#eess.AS

paper · pdf

Abstract

Linguistic Inquiry and Word Count (LIWC) provides auditable psycholinguistic categories that are widely used to interpret depression-related language, but its incremental predictive role in modern multimodal systems remains unclear. We evaluate LIWC across five English and Chinese depression-related corpora under matched participant-level cross-validation. We ask whether LIWC improves classification and what any performance change reflects. Intact LIWC is compared with three fold-local substitutes: a PCA-rotated version that removes direct access to named category coordinates, a participant-shuffled version that preserves real LIWC profiles while breaking participant alignment, and a random-marginal version that preserves feature-wise distributions. Across multiple fixed representation contexts, the results provide limited evidence for stable LIWC gains under frozen, participant-level early fusion. None of the prespecified dataset-blocked contrasts survives multiple-comparison correction. A separate SBERT calibration produces larger observed intact-versus-shuffled and intact-versus-random separations, indicating that larger participant-aligned signals can produce correspondingly larger separations under the same procedure, while not resolving the five-corpus power limitation. LIWC remains useful as an auditable, corpus-conditioned interpretive layer. These conclusions should not be generalized to fine-tuned, sequence-aware, or end-to-end architectures.

Citations

• WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning
• When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection
• Robust Speech Recognition via Large-Scale Weak Supervision
• Automatic Depression Detection: An Emotional Audio-Textual Corpus and a GRU/BiLSTM-based Model
• Unsupervised Cross-lingual Representation Learning for Speech\n Recognition
• MPNet: Masked and Permuted Pre-training for Language Understanding
• Towards Faithfully Interpretable NLP Systems: How should we define and\n evaluate faithfulness?
• Designing and Interpreting Probes with Control Tasks
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition
• A meta-analysis of correlations between depression and first person singular pronoun use
• The PHQ-8 as a measure of current depression in the general population
• A RATING SCALE FOR DEPRESSION

Related

• Multilingual Lexical Feature Analysis of Spoken Language for Predicting Major Depression Symptom Severity
• Systematic Evaluation of Machine-Generated Reasoning and PHQ-9 Labeling for Depression Detection Using Large Language Models
• DepressLLM: Interpretable domain-adapted language model for depression detection from real-world narratives
• Leveraging Large Language Models for Cost-Effective, Multilingual Depression Detection and Severity Assessment
• Evaluating Contextual Embeddings and their Extraction Layers for Depression Assessment