pannnnnnn
/

4_labels

@@ -1,199 +1,149 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
 ## Training Details
 ### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
 ### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
 ## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
 ### Testing Data, Factors & Metrics
 #### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
 #### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
 #### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
 ### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+pipeline_tag: text-classification
+language:
+- zh
+tags:
+- sentiment-analysis
+- mario
+- forum
+- off-topic-detection
+license: apache-2.0
+model-index:
+- name: pannnnnnn/4_labels
+  results:
+  - task:
+      type: text-classification
+      name: 4-way Sentiment + OT
+    metrics:
+    - type: accuracy
+      value: 0.854
+    - type: f1
+      name: macro_f1
+      value: 0.852
+    - type: f1
+      name: negative_f1
+      value: 0.939
+    - type: f1
+      name: neutral_f1
+      value: 0.774
+    - type: f1
+      name: positive_f1
+      value: 0.804
+    - type: f1
+      name: ot_f1
+      value: 0.891
 ---
+# pannnnnnn/4_labels
+## Model Summary
+這是一個 **中文論壇評論四分類模型**，輸入遊戲討論文字後，輸出以下四類標籤之一：
+- **0 = 負面**
+- **1 = 中立**
+- **2 = 正面**
+- **3 = OT (Off-topic, 離題)**
+模型專門應用於 **任天堂馬力歐系列遊戲**的社群評論（如 Dcard、Mobile01、PTT、巴哈姆特），研究目的是分析論壇情緒與股價走勢的關聯。
+特色：
+- **關鍵字白名單規則**：若文字（或任一分段）包含「奧德賽 / 3D世界 / 狂怒 / 創作家 / 馬創」，則強制視為非 OT。
+- **長文本切段**：對超過 512 token 的文字自動分段推論，最後取平均機率。
+- **一體化模型**：一次輸出四類，不需 Stage1 / Stage2。
+---
+## Model Details
+- **Developed by:** pannnnnnn
+- **Language(s):** zh-TW, zh-CN（主要為繁體中文）
+- **Model type:** Transformer (RoBERTa-zh base finetuned)
+- **License:** Research use (non-commercial)
+- **Finetuned from:** `hfl/chinese-roberta-wwm-ext`
+---
 ## Training Details
 ### Training Data
+- 來源：台灣遊戲論壇（Dcard、Mobile01、PTT、巴哈姆特），自建爬蟲收集。
+- 清理：去掉網址、簽名檔、重複貼文；正規化全半形字；保留 emoji。
+- 人工標註：四類（負面、中立、正面、OT）。
 ### Training Procedure
+- Optimizer: AdamW
+- Loss: CrossEntropy (focal loss variant)
+- Batch size: 32
+- Epochs: 3
+- Mixed precision: fp16
+---
 ## Evaluation
 ### Testing Data, Factors & Metrics
 #### Testing Data
+- **切分方式**：依 `timestamp` 欄位排序後，以時間先後劃分資料集。
+- **分配比例**：最後 10% 的資料作為 **Test Set**；倒數前 15% 作為 **Validation Set**；其餘為 **Training Set**。
+- **目的**：模擬「訓練只能使用過去資料，測試用未來資料」，避免資訊洩漏 (data leakage)。
 #### Factors
+- 不同子遊戲（如《奧德賽》《3D世界＋狂怒世界》《創作家》）在情緒分布上的差異。
+- 貼文長度（短文 vs 長文）對分類效果的影響。
 #### Metrics
+- Accuracy
+- Macro-F1
+- Per-class F1
 ### Results
+| Label | Precision | Recall | F1   | Support |
+|-------|-----------|--------|------|---------|
+| neg   | 0.964     | 0.915  | 0.939| 59      |
+| neu   | 0.789     | 0.759  | 0.774| 54      |
+| pos   | 0.738     | 0.882  | 0.804| 51      |
+| ot    | 0.930     | 0.855  | 0.891| 62      |
+| **Accuracy** | – | – | **0.854** | 226 |
+| **Macro avg** | 0.855 | 0.853 | 0.852 | – |
+| **Weighted avg** | 0.862 | 0.854 | 0.856 | – |
+---
+## Uses
+### Direct Use
+- 輸入論壇貼文 / 留言，判斷其情緒或是否離題。
+- 適合研究用途（例如：情緒與股價關聯分析、論壇口碑追蹤）。
+### Downstream Use
+- 可再微調到其他領域的四類情緒分類。
+- 可改成三類情緒（合併 OT 與中立）或二類情緒。
+### Out-of-Scope Use
+- 不適用於醫療、法律、金融決策。
+- 不適合處理極短、缺乏上下文的片段。
+---
+## Bias, Risks, Limitations
+- **資料來源偏差**：主要來自遊戲論壇，不能泛用到所有中文語境。
+- **諷刺/雙關困難**：模型可能誤判反諷、梗文。
+- **跨遊戲混淆**：若評論同時提及其他遊戲，判斷可能不準。
+**建議**：搭配人工檢視與統計，避免單一模型輸出直接做高風險決策。
+---
+## How to Use
+```python
+from transformers import pipeline
+pipe = pipeline("text-classification",
+                model="pannnnnnn/4_labels",
+                truncation=True,
+                top_k=None)
+print(pipe("這代真的比奧德賽更好玩！"))
+# [{'label': 'positive', 'score': 0.92}]