---
language: ar
license: apache-2.0
base_model: CAMeL-Lab/bert-base-arabic-camelbert-da
pipeline_tag: text-classification
tags:
- arabic
- text-classification
- stance-detection
- stanceeval-2026
- arabicnlp-2026
- track2-unseen-targets
---

# StanceEval-2026 — Track 2 (Unseen Targets): CAMeLBERT-DA

Arabic stance-detection classifier for [StanceEval-2026](https://stanceeval.github.io/StanceEval-2026/),
an ArabicNLP 2026 (@ EMNLP 2026, Budapest) shared task. Given an Arabic tweet and a target topic, the
model predicts whether the tweet's author is in **Favor** of, **Against**, or has **None**
(neutral/irrelevant) stance toward the target.

## Track 2: Unseen Targets

Trained on the Track 2 training pool, evaluated on target topics **not seen during training** (cross-target generalization). Train 2,721 / Dev 1,400 tweets (Mawqif-v2).

## Base model

`CAMeL-Lab/bert-base-arabic-camelbert-da`

## Labels

| ID | Label | Meaning |
|---|---|---|
| 0 | `Favor` | Tweet supports the target |
| 1 | `Against` | Tweet opposes the target |
| 2 | `None` | Neutral, irrelevant, or unclear stance |

## Dev set result

**74.98 Favg2** (dev set), the shared task's primary metric (macro-F1 over Favor + Against, None excluded).

## Usage

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("HassanB4/t2_s4_camelbert_text_target")
model = AutoModelForSequenceClassification.from_pretrained("HassanB4/t2_s4_camelbert_text_target")
model.eval()

id2label = {0: "Favor", 1: "Against", 2: "None"}

text = "..."
target = "..."
inputs = tokenizer(text, target, return_tensors="pt", truncation=True, max_length=512)

with torch.no_grad():
    logits = model(**inputs).logits

predicted_label = id2label[int(torch.argmax(logits, dim=-1)[0])]
print(predicted_label)
```

## Status

Part of the NAMAA Community StanceEval-2026 submission (Track 2). A system description paper
is in preparation; citation details will be added once available.