# Semeval2021task6 St3

> Detects persuasion techniques in multimodal memes by jointly analyzing text and image content. It probes cross-modal alignment and interaction modeling for persuasive content detection. Use when the user wants to benchmark on SemEval-2021 Task 6 Subtask 3, or asks about evaluating this task. Reports F1-Micro.

- Skill: `qhjqhj00/semeval2021task6-st3` (Agent Skill)
- Install (CLI): `npx skillmds add qhjqhj00/semeval2021task6-st3`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qhjqhj00/semeval2021task6-st3/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: qhjqhj00 (https://skillmd.com/u/qhjqhj00)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/qhjqhj00/semeval2021task6-st3

---


# semeval2021task6-st3

> SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images — Dimitrov et al. (2021) (arXiv:2105.09284, 2021)

## What this evaluates

Detects persuasion techniques in multimodal memes by jointly analyzing text and image content. It probes cross-modal alignment and interaction modeling for persuasive content detection.

## Datasets

- **SemEval-2021 Task 6 Subtask 3** — total ?; splits: test (-1)

## Metrics

- `F1-Micro` **(primary)** — range: [0, 1]
  - Micro-averaged F1 score for multimodal persuasion technique detection.

## Input / output format

**Input**: Paired text and image (meme).

**Output**: Multilabel classification of persuasion techniques present in the meme.

## Scoring recipe

```python
tp = fp = fn = 0
for p, g in zip(predictions, golds):
    for label in all_labels:
        if label in p and label in g: tp += 1
        elif label in p and label not in g: fp += 1
        elif label not in p and label in g: fn += 1
prec = tp / (tp + fp) if (tp + fp) > 0 else 0
rec = tp / (tp + fn) if (tp + fn) > 0 else 0
return 2 * prec * rec / (prec + rec) if (prec + rec) > 0 else 0
```

## Common pitfalls

- Modeling modality interaction is more important than simple feature fusion.
- Text and image representations often use different architectures (e.g., BERT for text, ResNet for images) requiring careful alignment.

## Evidence (verbatim from paper)

> The evaluation results are shown in Table 3... The systems are ordered by the official score: F1-micro. Subtask 3 (Multimodal: Memes)... This is a very rich and very interesting table. We can see that transformers were quite popular for text representation... For the visual modality, the most common representations were variants of ResNet...

## Citation

```bibtex
@misc{dimitrov2021semevaltask6,
  title={SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images},
  author={Dimitrov et al. (2021)},
  year={2021},
  note={arXiv:2105.09284}
}
```

- arXiv: 2105.09284