Conference paper · 2026 · Open access
When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews
Language Resources and Evaluation Conference (LREC), 2355–2361 · Published 1 May 2026 · DOI 10.63317/34hw23mzd8c7
In brief
“When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews” is a 2026 conference paper by Hasindri Watawana and 6 co-authors, published in Language Resources and Evaluation Conference (LREC). OpenAlex counts 2 citations as of 22 November 2026, which puts it in the top 6% of works published in 2026 by citations. It is open access: the full text is free to read at Language Resources and Evaluation Conference (LREC).
- Citations
- 2
- Most cited in
- 2026 (2)
- Field-weighted impact
- 1.28
- References
- 19
- Authors
- 7
Abstract
Automatic depression detection from doctor-patient conversations has gained momentum thanks to the availability of public corpora and advances in language modeling.However, interpretability remains limited: strong performance is often reported without revealing what drives predictions.We analyze three datasets-ANDROIDS, DAIC-WOZ, and E-DAIC-and identify a systematic bias from interviewer prompts in semi-structured interviews.Models trained on interviewer turns exploit fixed prompts and positions to distinguish depressed from control subjects, often achieving high classification scores without using participant language.Restricting models to participant utterances distributes decision evidence more broadly and reflects genuine linguistic cues.While semi-structured protocols ensure consistency, including interviewer prompts inflates performance by leveraging script artifacts.Our results highlight a cross-dataset, architecture-agnostic bias and emphasize the need for analyses that localize decision evidence by time and speaker to ensure models learn from participants' language.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Watawana, H., Burdisso, S., Moreno-Galván, D. A., Sánchez-Vega, F., López-Monroy, A. P., Motlíček, P., & Villatoro-Tello, E. (2026). When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews. Language Resources and Evaluation Conference (LREC), 2355–2361. https://doi.org/10.63317/34hw23mzd8c7
MLA 9
Watawana, Hasindri, et al. “When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews.” Language Resources and Evaluation Conference (LREC), 2026, pp. 2355–2361. https://doi.org/10.63317/34hw23mzd8c7.
Chicago
Watawana, Hasindri, Sergio Burdisso, Diego Aarón Moreno-Galván, Fernando Sánchez-Vega, Adrián Pastor López-Monroy, Petr Motlíček, and Esaú Villatoro-Tello. 2026. “When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews.” Language Resources and Evaluation Conference (LREC): 2355–2361. https://doi.org/10.63317/34hw23mzd8c7.
Harvard
Watawana, H. et al. (2026) ‘When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews’, Language Resources and Evaluation Conference (LREC), pp. 2355–2361. doi:10.63317/34hw23mzd8c7.
IEEE
H. Watawana et al., “When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews,” Language Resources and Evaluation Conference (LREC), pp. 2355–2361, 2026, doi: 10.63317/34hw23mzd8c7.
BibTeX
@inproceedings{watawana2026when,
title = {{When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews}},
author = {Watawana, Hasindri and Burdisso, Sergio and Moreno-Galván, Diego Aarón and Sánchez-Vega, Fernando and López-Monroy, Adrián Pastor and Motlíček, Petr and Villatoro-Tello, Esaú},
booktitle = {Language Resources and Evaluation Conference (LREC)},
year = {2026},
pages = {2355--2361},
doi = {10.63317/34hw23mzd8c7},
url = {https://doi.org/10.63317/34hw23mzd8c7}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- automatic depression detection
- doctor-patient conversation
- bias in language models
- interpretability
- Android
- DAIC-WOZ
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Watawana, H., Burdisso, S., Moreno-Galván, D. A., Sánchez-Vega, F., López-Monroy, A. P., Motlíček, P., & Villatoro-Tello, E. (2026). When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews. Language Resources and Evaluation Conference (LREC), 2355–2361. https://doi.org/10.63317/34hw23mzd8c7
How many times has this paper been cited?
2 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Language Resources and Evaluation Conference (LREC): sign in and open the PDF from this page.
Who wrote this paper?
Hasindri Watawana, Sergio Burdisso, Diego Aarón Moreno-Galván, Fernando Sánchez-Vega, Adrián Pastor López-Monroy, Petr Motlíček, Esaú Villatoro-Tello.
What is the DOI of this paper?
10.63317/34hw23mzd8c7, permanently at https://doi.org/10.63317/34hw23mzd8c7. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.