Browse State-of-the-Art › Stance Detection

Stance Detection

127 papers with code · 22 benchmarks · 35 datasets archive 2025-07-28

Natural Language Processing

Stance detection is the extraction of a subject's reaction to a claim made by a primary actor. It is a core part of a set of approaches to fake news assessment.

Example:

  • Source: "Apples are the most delicious fruit in existence"
  • Reply: "Obviously not, because that is a reuben from Katz's"
  • Stance: deny

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

22 leaderboard tables shown for this task, 22 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 22 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MGTAB (4 rows) RGT MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmark code — Compare
RumourEval (3 rows) Kochkina et al. 2017 Turing at SemEval-2017 Task 8: Sequential Approach to Rumour... code — Compare
FNC-1 (2 rows) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
ARC (AI2 Reasoning Challenge) (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
argmin (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
Dhoroni (1 row) BanglaBERT-Dhoroni Dhoroni: Exploring Bengali Climate Change and Environmental Views... code — Compare
emergent (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
iac1 (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
ibmcs (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
mtsd (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
P-Stance (1 row) COLA+GPT3.5 Stance Detection with Collaborative Role-Infused LLM-Based Agents code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
Perspectrum (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
poldeb (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
RuStance (1 row) Boosting Stance Prediction for Russian: Data and Analysis code — Compare
SCD (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
SemEval 2019 (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
Snopes (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
STEDUCOV: A DATASET ON STANCE DETECTION IN TWEETS TOWARDS ONLINE EDUCATION DURING COVID-19 PANDEMIC (1 row) BERT StEduCov: An Explored and Benchmarked Dataset on Stance Detection... — — Compare
Trump Midterm Elections 2018 (1 row) MUSE + UMAP (Unsupervised) Embeddings-Based Clustering for Target Specific Stances: The Case... code — Compare
Turkish Elections 2018 (1 row) MUSE + UMAP (Unsupervised) Embeddings-Based Clustering for Target Specific Stances: The Case... code — Compare
VAST (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare
wtwt (1 row) TESTED Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

35 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 35 until expanded.

Subtasks archive 2025-07-28

4 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 343 · with a code link: 127 · where Syntology ran a sample: 9 (6 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (9 of 343 tagged: 6 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 4: papers 1 to 100 of 343, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 9 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections