Update README.md

README.md

@@ -11,15 +11,16 @@ language:
 # Amazon Reviews Sentiment Analysis Model
 
 ## Model Description
-This model is a **sentiment analysis model** trained on the **Amazon Reviews dataset** to classify customer reviews into sentiment categories (e.g., positive, negative, neutral depending on configuration).
-It is designed for:
-* Learning and research purposes
-* NLP experimentation
-* Academic projects
-* Non-commercial applications
+This model is a **sentiment analysis model** fine-tuned using **BertForSequenceClassification** on the **Amazon Reviews dataset**.
+It classifies Amazon product reviews into sentiment categories: negative, neutral, or positive.
+Intended for **research, educational, and non-commercial use only**.
 
-The model is based on a **Transformer architecture (BERT-based)** and fine-tuned specifically for sentiment classification tasks.
+---
 
+## Base Model
+* **bert-base-uncased**
+* Architecture: Transformer (BERT)
+* Head: Sequence Classification
 ---
 
 ## Intended Use
@@ -27,27 +28,27 @@ The model is based on a **Transformer architecture (BERT-based)** and fine-tuned
 ### ✅ Allowed Uses
 * Academic research
 * Educational projects
-* Personal experimentation
+* Personal learning
 * Non-commercial applications
-* Benchmarking and evaluation
+* Experiments and benchmarking
 
 ### ❌ Prohibited Uses
 * Commercial use
 * Selling or reselling the model
-* Monetized APIs or SaaS products
-* Integration into paid software or services
+* Paid APIs or SaaS products
+* Monetized applications or services
 
-> **Note:** Commercial use is strictly prohibited under the CC BY-NC 4.0 license.
+Commercial use is **strictly prohibited** under the CC BY-NC 4.0 license.
 
 ---
 
 ## Training Data
-The model was trained on the **Amazon Reviews dataset**, which contains user-generated product reviews and ratings from Amazon.
+Trained on the **Amazon Reviews dataset**:
 * Language: English
 * Domain: E-commerce product reviews
 * Data type: Text reviews with sentiment labels
 
-The original dataset creators retain their respective rights. Please refer to the dataset’s original license and terms for more details.
+The original dataset creators retain all rights to the data. Users should consult the dataset’s original license for details.
 
 ---
 
@@ -56,11 +57,9 @@ The original dataset creators retain their respective rights. Please refer to th
 * Framework: Hugging Face Transformers
 * Number of labels: 3
 * Loss Function: Cross-entropy loss
-* Training was performed using device-agnostic code (GPU if available, otherwise CPU)
+* Training performed on GPU if available, otherwise CPU
 
 ### Label Mapping
-The sentiment labels used by the model are mapped as follows:
-
 | Label ID | Sentiment |
 | -------- | --------- |
 | 0        | Negative  |
@@ -70,59 +69,45 @@ The sentiment labels used by the model are mapped as follows:
 ---
 
 ## Evaluation
-The model was evaluated using a **multi-class classification report** with three sentiment categories:
+Evaluated using a **multi-class classification report** with three categories:
 * Negative
 * Neutral
 * Positive
 
-Evaluation metrics include:
-* Precision
-* Recall
-* F1-score
-* Support (per class)
-
-The classification report was generated using standard tools such as `sklearn.metrics.classification_report`.
-Performance may vary depending on product category, writing style, and domain shift.
+Metrics include precision, recall, F1-score, and support (per class).
+Performance may vary depending on product category and review style.
 
 ---
 
 ## Limitations and Bias
-* The model reflects biases present in Amazon user reviews
-* Performance may degrade on non-product-related text
-* Not suitable for languages other than English
-* May not generalize well to informal or domain-specific slang
-
-Users are encouraged to evaluate the model on their own datasets before deployment.
-
+* Reflects biases in Amazon reviews
+* May not perform well on non-product text
+* Not suitable for non-English languages
+* Predictions are subjective, not factual judgments
 ---
 
 ## Ethical Considerations
-* This model analyzes user-generated content, which may include biased or subjective opinions
-* Predictions should not be treated as factual judgments
-* Not intended for high-stakes decision-making
+Analyze subjective content only; not for high-stakes decisions.
 
 ---
 
 ## How to Use
-
 ```python
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
-model_name = "mianzaka/sentiment-analysis-model/"
+model_name = "mianzaka/sentiment-analysis-model"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
 text = "The product quality is decent but delivery was slow."
-
 inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
 
 with torch.no_grad():
     outputs = model(**inputs)
 
 predicted_label = torch.argmax(outputs.logits, dim=1).item()
-
 label_map = {0: "Negative", 1: "Neutral", 2: "Positive"}
 print("Predicted sentiment:", label_map[predicted_label])
 ```
@@ -130,25 +115,22 @@ print("Predicted sentiment:", label_map[predicted_label])
 ---
 
 ## License
-This model is released under the **Creative Commons Attribution-NonCommercial 4.0 (CC BY-NC 4.0)** license.
-**Commercial use, resale, or monetization of this model is strictly prohibited.**
-For more details, see the full license text: [https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)
+Released under **CC BY-NC 4.0**. Commercial use, resale, or monetization is prohibited.
+Full license: [https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)
 
 ---
 
 ## Citation
-If you use this model in your research or projects, please cite:
-
 ```bibtex
 @misc{sentiment-analysis-model,
-  author       = {Mian Zaka},
-  title        = {Amazon Reviews Sentiment Analysis Model},
-  year         = {2026},
-  publisher    = {Hugging Face}
+  author = {Mian Zaka},
+  title  = {Amazon Reviews Sentiment Analysis Model},
+  year   = {2026},
+  publisher = {Hugging Face}
 }
 ```
 
 ---
 
 ## Contact
-For questions, feedback, or licensing inquiries, please contact the model author via Hugging Face.
+For questions or feedback, contact the model author via Hugging Face.