FutureMa / stance_ch

huggingface.co
Total runs: 1
24-hour runs: 0
7-day runs: 1
30-day runs: 1
Model's Last Updated: September 08 2025
text-classification

Introduction of stance_ch

Model Details of stance_ch

Chinese BERT for Stance Analysis (立场分析)

这是一个基于BERT的中文立场分析模型,能够识别文本中表达的支持(SUPPORTIVE)或反对(OPPOSING)立场。

模型信息
  • 模型基础 : bert-base-chinese
  • 任务类型 : 二分类文本分类
  • 语言 : 中文 (Chinese)
  • 训练数据 : 包含6,668条立场标注数据
  • 标签 : OPPOSING (反对), SUPPORTIVE (支持)
性能指标
指标 数值
验证集准确率 N/A
测试集准确率 N/A
训练轮数 N/A
使用方法
from transformers import BertTokenizer, BertForSequenceClassification
import torch

# 加载模型和tokenizer
model_name = "FutureMa/stance_ch"
tokenizer = BertTokenizer.from_pretrained(model_name)
model = BertForSequenceClassification.from_pretrained(model_name)

# 示例预测
def predict_stance(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
    
    with torch.no_grad():
        outputs = model(**inputs)
        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
        predicted_class = torch.argmax(predictions, dim=-1).item()
    
    labels = {"0": "OPPOSING", "1": "SUPPORTIVE"}
    confidence = predictions[0][predicted_class].item()
    
    return {
        "stance": labels[str(predicted_class)],
        "confidence": confidence
    }

# 使用示例
text = "我完全支持这个政策,它对社会发展有积极作用。"
result = predict_stance(text)
print(f"立场: {result['stance']}, 置信度: {result['confidence']:.4f}")
数据格式

训练数据采用以下格式:

topic: [话题内容]
answer: [回答内容]

模型基于回答内容判断其对话题的立场。

标签说明
  • OPPOSING (0): 反对立场
  • SUPPORTIVE (1): 支持立场
训练详情
  • 优化器 : AdamW
  • 学习率 : 2e-5
  • 批次大小 : 16
  • 最大序列长度 : 512
  • 早停策略 : 验证集准确率连续3轮无提升
  • 数据划分 : 训练集 6,268 / 验证集 200 / 测试集 200
注意事项
  1. 模型主要针对中文文本训练
  2. 最佳输入长度为512个token以内
  3. 模型对政治、社会话题的立场分析效果较好
  4. 建议在使用前对特定领域数据进行微调
许可证

本模型遵循Apache-2.0许可证。

引用

如果使用本模型,请引用:

@misc{stance_ch_2025,
  title={Chinese BERT for Stance Analysis},
  author={FutureMa},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/FutureMa/stance_ch}
}

模型训练时间: 2025年09月07日

Runs of FutureMa stance_ch on huggingface.co

1
Total runs
0
24-hour runs
0
3-day runs
1
7-day runs
1
30-day runs

More Information About stance_ch huggingface.co Model

stance_ch huggingface.co

stance_ch huggingface.co is an AI model on huggingface.co that provides stance_ch's model effect (), which can be used instantly with this FutureMa stance_ch model. huggingface.co supports a free trial of the stance_ch model, and also provides paid use of the stance_ch. Support call stance_ch model through api, including Node.js, Python, http.

FutureMa stance_ch online free

stance_ch huggingface.co is an online trial and call api platform, which integrates stance_ch's modeling effects, including api services, and provides a free online trial of stance_ch, you can try stance_ch online for free by clicking the link below.

FutureMa stance_ch online free url in huggingface.co:

https://huggingface.co/FutureMa/stance_ch

stance_ch install

stance_ch is an open source model from GitHub that offers a free installation service, and any user can find stance_ch on GitHub to install. At the same time, huggingface.co provides the effect of stance_ch install, users can directly use stance_ch installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

stance_ch install url in huggingface.co:

https://huggingface.co/FutureMa/stance_ch

Url of stance_ch

stance_ch huggingface.co Url

Provider of stance_ch huggingface.co

FutureMa
ORGANIZATIONS

Other API from FutureMa

huggingface.co

Total runs: 197
Run Growth: -1.1K
Growth Rate: -555.33%
Updated:February 10 2026
huggingface.co

Total runs: 85
Run Growth: -447
Growth Rate: -525.88%
Updated:January 18 2026
huggingface.co

Total runs: 5
Run Growth: -7
Growth Rate: -140.00%
Updated:January 12 2026
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:December 22 2023
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:February 28 2025
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:February 27 2025