Deep Learning in Stance Detection: A Survey
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The analysis of an author’s perspective on a given topic within text presents a challenging problem in natural language processing. Stance detection, or the identification of an author’s inclination either in favor, against, or neutral toward some target entity, is an important classification task in this context. Significant progress has been made in stance detection, especially facilitated by deep learning. This survey explores these approaches as applied to the vanilla stance detection problem, as well as its sub-problems, including cross-target, cross-domain, multi-target, cross-lingual, and multi-lingual stance detection. We also overview methods leveraging deep learning for zero- and few-shot learning-based stance detection. The survey also overview generative large language models for stance detection and highlights various research opportunities, including devising models to improve cross-domain learning, advancing models for implicit stance detection, enhancing explainability in stance detection models, addressing scalability and computational cost challenges, and accommodating evolving stance labels.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it