update

inference.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
 """
-Inference script for Pulse Core 1 - Vietnamese Aspect Sentiment Analysis.
+Inference script for Pulse Core 1 - Vietnamese Sentiment Analysis System.
 Loads trained sentiment models from local files and performs predictions.
+Supports both VLSP2016 general sentiment and UTS2017_Bank aspect sentiment models.
 """
 
 import argparse
@@ -20,22 +21,34 @@ def find_local_models():
     # Find exported sentiment models in project root
     for filename in os.listdir('.'):
         if filename.endswith('.joblib'):
-            if filename.startswith('uts2017_sentiment_'):
+            if filename.startswith('vlsp2016_sentiment_'):
+                models['exported']['vlsp2016_sentiment'] = filename
+            elif filename.startswith('uts2017_sentiment_'):
                 models['exported']['uts2017_sentiment'] = filename
 
     # Find models in runs directory - prioritize SVC models
-    sentiment_runs = glob.glob('runs/*/models/UTS2017_Bank_AspectSentiment_*.joblib')
+    vlsp_runs = glob.glob('runs/*/models/VLSP2016_Sentiment_*.joblib')
+    uts_runs = glob.glob('runs/*/models/UTS2017_Bank_AspectSentiment_*.joblib')
 
-    if sentiment_runs:
+    if vlsp_runs:
         # Sort by modification time (most recent first)
-        sentiment_runs.sort(key=lambda x: os.path.getmtime(x), reverse=True)
+        vlsp_runs.sort(key=lambda x: os.path.getmtime(x), reverse=True)
+        # Prefer SVC models over other types
+        svc_models = [m for m in vlsp_runs if 'SVC' in m]
+        if svc_models:
+            models['runs']['vlsp2016_sentiment'] = svc_models[0]  # Most recent SVC
+        else:
+            models['runs']['vlsp2016_sentiment'] = vlsp_runs[0]  # Most recent any model
 
+    if uts_runs:
+        # Sort by modification time (most recent first)
+        uts_runs.sort(key=lambda x: os.path.getmtime(x), reverse=True)
         # Prefer SVC models over other types
-        svc_models = [m for m in sentiment_runs if 'SVC' in m]
+        svc_models = [m for m in uts_runs if 'SVC' in m]
         if svc_models:
             models['runs']['uts2017_sentiment'] = svc_models[0]  # Most recent SVC
         else:
-            models['runs']['uts2017_sentiment'] = sentiment_runs[0]  # Most recent any model
+            models['runs']['uts2017_sentiment'] = uts_runs[0]  # Most recent any model
 
     return models
 
@@ -78,9 +91,14 @@ def predict_text(model, text):
 def interactive_mode(model, dataset_name):
     """Interactive prediction mode"""
     print(f"\n{'='*60}")
-    print("INTERACTIVE MODE - VIETNAMESE BANKING ASPECT SENTIMENT ANALYSIS")
-    print(f"{'='*60}")
-    print("Enter Vietnamese banking text to analyze aspect and sentiment (type 'quit' to exit):")
+    if dataset_name == 'vlsp2016_sentiment':
+        print("INTERACTIVE MODE - VIETNAMESE GENERAL SENTIMENT ANALYSIS")
+        print(f"{'='*60}")
+        print("Enter Vietnamese text to analyze sentiment (type 'quit' to exit):")
+    else:
+        print("INTERACTIVE MODE - VIETNAMESE BANKING ASPECT SENTIMENT ANALYSIS")
+        print(f"{'='*60}")
+        print("Enter Vietnamese banking text to analyze aspect and sentiment (type 'quit' to exit):")
 
     while True:
         try:
@@ -109,23 +127,39 @@ def interactive_mode(model, dataset_name):
 
 
 def test_examples(model, dataset_name):
-    """Test model with predefined banking examples"""
-    examples = [
-        "Tôi muốn mở tài khoản tiết kiệm mới",
-        "Lãi suất vay mua nhà hiện tại quá cao",
-        "Làm thế nào để đăng ký internet banking?",
-        "Chi phí chuyển tiền ra nước ngoài rất đắt",
-        "Ngân hàng ACB có uy tín không?",
-        "Tôi cần hỗ trợ về dịch vụ ngân hàng",
-        "Thẻ tín dụng bị khóa không rõ lý do",
-        "Dịch vụ chăm sóc khách hàng rất tệ",
-        "Khuyến mãi tháng này rất hấp dẫn",
-        "Bảo mật tài khoản có được đảm bảo không?"
-    ]
-
-    print("\n" + "="*60)
-    print("TESTING VIETNAMESE BANKING ASPECT SENTIMENT ANALYSIS")
-    print("="*60)
+    """Test model with predefined examples based on dataset type"""
+    if dataset_name == 'vlsp2016_sentiment':
+        examples = [
+            "Sản phẩm này rất tốt, tôi rất hài lòng",
+            "Chất lượng dịch vụ tệ quá",
+            "Giá cả hợp lý, có thể chấp nhận được",
+            "Nhân viên phục vụ rất nhiệt tình",
+            "Đồ ăn không ngon, sẽ không quay lại",
+            "Giao hàng nhanh chóng, đóng gói cẩn thận",
+            "Sản phẩm bình thường, không có gì đặc biệt",
+            "Rất đáng tiền, chất lượng tuyệt vời",
+            "Không như mong đợi, khá thất vọng",
+            "Dịch vụ khách hàng tốt, giải quyết nhanh chóng"
+        ]
+        print("\n" + "="*60)
+        print("TESTING VIETNAMESE GENERAL SENTIMENT ANALYSIS")
+        print("="*60)
+    else:
+        examples = [
+            "Tôi muốn mở tài khoản tiết kiệm mới",
+            "Lãi suất vay mua nhà hiện tại quá cao",
+            "Làm thế nào để đăng ký internet banking?",
+            "Chi phí chuyển tiền ra nước ngoài rất đắt",
+            "Ngân hàng ACB có uy tín không?",
+            "Tôi cần hỗ trợ về dịch vụ ngân hàng",
+            "Thẻ tín dụng bị khóa không rõ lý do",
+            "Dịch vụ chăm sóc khách hàng rất tệ",
+            "Khuyến mãi tháng này rất hấp dẫn",
+            "Bảo mật tài khoản có được đảm bảo không?"
+        ]
+        print("\n" + "="*60)
+        print("TESTING VIETNAMESE BANKING ASPECT SENTIMENT ANALYSIS")
+        print("="*60)
 
     for text in examples:
         prediction, confidence, top_predictions = predict_text(model, text)
@@ -147,30 +181,41 @@ def list_available_models():
     """List all available sentiment models"""
     models = find_local_models()
 
-    print("Available Vietnamese Aspect Sentiment Models:")
+    print("Available Vietnamese Sentiment Models:")
     print("=" * 50)
 
     if models['exported']:
         print("\nExported Models (Project Root):")
         for model_type, filename in models['exported'].items():
             file_size = os.path.getsize(filename) / (1024 * 1024)  # MB
-            print(f"  {model_type}: {filename} ({file_size:.1f}MB)")
+            dataset_type = "General Sentiment" if "vlsp2016" in model_type else "Banking Aspect Sentiment"
+            print(f"  {model_type}: {filename} ({file_size:.1f}MB) - {dataset_type}")
 
     if models['runs']:
         print("\nRuns Models (Training Directory):")
         for model_type, filepath in models['runs'].items():
             file_size = os.path.getsize(filepath) / (1024 * 1024)  # MB
-            print(f"  {model_type}: {filepath} ({file_size:.1f}MB)")
+            dataset_type = "General Sentiment" if "vlsp2016" in model_type else "Banking Aspect Sentiment"
+            print(f"  {model_type}: {filepath} ({file_size:.1f}MB) - {dataset_type}")
 
     if not models['exported'] and not models['runs']:
         print("No local sentiment models found!")
-        print("Train a model first using: python train.py --export-model")
+        print("Train a model first using:")
+        print("  VLSP2016: python train.py --dataset vlsp2016 --export-model")
+        print("  UTS2017:  python train.py --dataset uts2017 --export-model")
 
 
 def main():
     """Main function"""
     parser = argparse.ArgumentParser(
-        description="Inference with local Pulse Core 1 Vietnamese aspect sentiment models"
+        description="Inference with local Pulse Core 1 Vietnamese sentiment models"
+    )
+    parser.add_argument(
+        "--dataset",
+        type=str,
+        choices=["vlsp2016", "uts2017", "auto"],
+        default="auto",
+        help="Dataset type to use (default: auto-detect)"
     )
     parser.add_argument(
         "--model-path",
@@ -180,12 +225,12 @@ def main():
     parser.add_argument(
         "--text",
         type=str,
-        help="Vietnamese banking text to analyze (if not provided, enters interactive mode)"
+        help="Vietnamese text to analyze (if not provided, enters interactive mode)"
     )
     parser.add_argument(
         "--test-examples",
         action="store_true",
-        help="Test with predefined banking examples"
+        help="Test with predefined examples"
     )
     parser.add_argument(
         "--list-models",
@@ -210,22 +255,54 @@ def main():
     # Find available models
     models = find_local_models()
 
-    # Determine model path
+    # Determine model path and dataset
     model_path = None
-    dataset_name = "uts2017_sentiment"
+    dataset_name = None
 
     if args.model_path:
         # Use specified model path
         model_path = args.model_path
-    else:
-        # Auto-select sentiment model
-        if models[args.source] and 'uts2017_sentiment' in models[args.source]:
-            model_path = models[args.source]['uts2017_sentiment']
-            print("Auto-selected UTS2017 sentiment model")
+        # Try to detect dataset from filename
+        if 'vlsp2016' in args.model_path:
+            dataset_name = 'vlsp2016_sentiment'
+        elif 'uts2017' in args.model_path:
+            dataset_name = 'uts2017_sentiment'
         else:
-            print("No sentiment models found!")
-            list_available_models()
-            return
+            dataset_name = 'unknown'
+    else:
+        # Auto-select or use specified dataset
+        if args.dataset == 'vlsp2016':
+            if models[args.source] and 'vlsp2016_sentiment' in models[args.source]:
+                model_path = models[args.source]['vlsp2016_sentiment']
+                dataset_name = 'vlsp2016_sentiment'
+                print("Selected VLSP2016 general sentiment model")
+            else:
+                print("No VLSP2016 models found!")
+                list_available_models()
+                return
+        elif args.dataset == 'uts2017':
+            if models[args.source] and 'uts2017_sentiment' in models[args.source]:
+                model_path = models[args.source]['uts2017_sentiment']
+                dataset_name = 'uts2017_sentiment'
+                print("Selected UTS2017 banking aspect sentiment model")
+            else:
+                print("No UTS2017 models found!")
+                list_available_models()
+                return
+        else:  # auto
+            # Prefer VLSP2016 if available, otherwise UTS2017
+            if models[args.source] and 'vlsp2016_sentiment' in models[args.source]:
+                model_path = models[args.source]['vlsp2016_sentiment']
+                dataset_name = 'vlsp2016_sentiment'
+                print("Auto-selected VLSP2016 general sentiment model")
+            elif models[args.source] and 'uts2017_sentiment' in models[args.source]:
+                model_path = models[args.source]['uts2017_sentiment']
+                dataset_name = 'uts2017_sentiment'
+                print("Auto-selected UTS2017 banking aspect sentiment model")
+            else:
+                print("No sentiment models found!")
+                list_available_models()
+                return
 
     if not model_path or not os.path.exists(model_path):
         print(f"Model file not found: {model_path}")
@@ -255,7 +332,8 @@ def main():
 
     else:
         # Interactive mode
-        print(f"Loaded sentiment model: {os.path.basename(model_path)}")
+        model_type = "General Sentiment" if dataset_name == 'vlsp2016_sentiment' else "Banking Aspect Sentiment"
+        print(f"Loaded {model_type} model: {os.path.basename(model_path)}")
         test_examples(model, dataset_name)
 
         # Ask if user wants interactive mode

use_this_model.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """
-Demonstration script for using Pulse Core 1 - Vietnamese Banking Aspect Sentiment Analysis from Hugging Face Hub.
-Shows how to download and use the pre-trained aspect sentiment model.
+Demonstration script for using Pulse Core 1 - Vietnamese Sentiment Analysis System from Hugging Face Hub.
+Shows how to download and use the pre-trained sentiment models for both general sentiment and banking aspect sentiment.
 """
 
 from huggingface_hub import hf_hub_download
@@ -31,10 +31,19 @@ def predict_text(model, text):
         return None, 0, []
 
 
-def load_model_from_hub():
-    """Load the pre-trained Pulse Core 1 banking aspect sentiment model from Hugging Face Hub"""
-    filename = "uts2017_sentiment_20250928_131716.joblib"
-    print("Downloading Pulse Core 1 (Vietnamese Banking Aspect Sentiment) model from Hugging Face Hub...")
+def load_model_from_hub(model_type="vlsp2016"):
+    """Load the pre-trained Pulse Core 1 sentiment model from Hugging Face Hub
+    Args:
+        model_type: 'vlsp2016' for general sentiment or 'uts2017' for banking aspect sentiment
+    """
+    if model_type == "vlsp2016":
+        filename = "vlsp2016_sentiment_20250929_075529.joblib"
+        print("Downloading Pulse Core 1 (Vietnamese General Sentiment) model from Hugging Face Hub...")
+        classes_desc = "sentiment classes (positive, negative, neutral)"
+    else:
+        filename = "uts2017_sentiment_20250928_131716.joblib"
+        print("Downloading Pulse Core 1 (Vietnamese Banking Aspect Sentiment) model from Hugging Face Hub...")
+        classes_desc = "aspect-sentiment combinations"
 
     try:
         model_path = hf_hub_download("undertheseanlp/pulse_core_1", filename)
@@ -42,9 +51,9 @@ def load_model_from_hub():
 
         print("Loading model...")
         model = joblib.load(model_path)
-        print(f"Model loaded successfully. Classes: {len(model.classes_)} aspect-sentiment combinations")
+        print(f"Model loaded successfully. Classes: {len(model.classes_)} {classes_desc}")
         print(f"Model type: {type(model.named_steps['clf']).__name__}")
-        return model
+        return model, model_type
     except Exception as e:
         print(f"Error downloading model: {e}")
         print("This might mean the model file hasn't been uploaded to Hugging Face Hub yet.")
@@ -52,41 +61,61 @@ def load_model_from_hub():
         raise
 
 
-def predict_banking_examples(model):
-    """Demonstrate predictions on Vietnamese banking aspect sentiment examples"""
-    print("\n" + "="*60)
-    print("VIETNAMESE BANKING ASPECT SENTIMENT ANALYSIS EXAMPLES")
-    print("="*60)
+def predict_sentiment_examples(model, model_type):
+    """Demonstrate predictions on Vietnamese sentiment examples"""
+    if model_type == "vlsp2016":
+        print("\n" + "="*60)
+        print("VIETNAMESE GENERAL SENTIMENT ANALYSIS EXAMPLES")
+        print("="*60)
+
+        # Vietnamese general sentiment examples
+        examples = [
+            ("positive", "Sản phẩm này rất tốt, tôi rất hài lòng"),
+            ("negative", "Chất lượng dịch vụ tệ quá"),
+            ("neutral", "Giá cả hợp lý, có thể chấp nhận được"),
+            ("positive", "Nhân viên phục vụ rất nhiệt tình"),
+            ("negative", "Đồ ăn không ngon, sẽ không quay lại"),
+            ("positive", "Giao hàng nhanh chóng, đóng gói cẩn thận"),
+            ("neutral", "Sản phẩm bình thường, không có gì đặc biệt"),
+            ("positive", "Rất đáng tiền, chất lượng tuyệt vời"),
+            ("negative", "Không như mong đợi, khá thất vọng"),
+            ("positive", "Dịch vụ khách hàng tốt, giải quyết nhanh chóng")
+        ]
+        print("Testing Vietnamese general sentiment analysis:")
+    else:
+        print("\n" + "="*60)
+        print("VIETNAMESE BANKING ASPECT SENTIMENT ANALYSIS EXAMPLES")
+        print("="*60)
+
+        # Vietnamese banking examples with expected aspect-sentiment combinations
+        examples = [
+            ("CUSTOMER_SUPPORT#negative", "Dịch vụ chăm sóc khách hàng rất tệ"),
+            ("CUSTOMER_SUPPORT#positive", "Nhân viên hỗ trợ rất nhiệt tình"),
+            ("TRADEMARK#positive", "Ngân hàng ACB có uy tín tốt"),
+            ("TRADEMARK#negative", "Thương hiệu ngân hàng này không đáng tin cậy"),
+            ("LOAN#positive", "Lãi suất vay mua nhà rất ưu đãi"),
+            ("LOAN#negative", "Lãi suất vay quá cao, không chấp nhận được"),
+            ("INTEREST_RATE#negative", "Lãi suất tiết kiệm thấp quá"),
+            ("INTEREST_RATE#positive", "Lãi suất gửi tiết kiệm khá hấp dẫn"),
+            ("CARD#negative", "Thẻ tín dụng bị khóa không rõ lý do"),
+            ("CARD#positive", "Thẻ ATM rất tiện lợi khi sử dụng"),
+            ("INTERNET_BANKING#negative", "Internet banking hay bị lỗi"),
+            ("INTERNET_BANKING#positive", "Ứng dụng ngân hàng điện tử dễ sử dụng"),
+            ("MONEY_TRANSFER#negative", "Phí chuyển tiền quá đắt"),
+            ("PROMOTION#positive", "Chương trình khuyến mãi rất hấp dẫn"),
+            ("SECURITY#positive", "Bảo mật tài khoản rất tốt")
+        ]
+        print("Testing Vietnamese banking aspect sentiment analysis:")
 
-    # Vietnamese banking examples with expected aspect-sentiment combinations
-    examples = [
-        ("CUSTOMER_SUPPORT#negative", "Dịch vụ chăm sóc khách hàng rất tệ"),
-        ("CUSTOMER_SUPPORT#positive", "Nhân viên hỗ trợ rất nhiệt tình"),
-        ("TRADEMARK#positive", "Ngân hàng ACB có uy tín tốt"),
-        ("TRADEMARK#negative", "Thương hiệu ngân hàng này không đáng tin cậy"),
-        ("LOAN#positive", "Lãi suất vay mua nhà rất ưu đãi"),
-        ("LOAN#negative", "Lãi suất vay quá cao, không chấp nhận được"),
-        ("INTEREST_RATE#negative", "Lãi suất tiết kiệm thấp quá"),
-        ("INTEREST_RATE#positive", "Lãi suất gửi tiết kiệm khá hấp dẫn"),
-        ("CARD#negative", "Thẻ tín dụng bị khóa không rõ lý do"),
-        ("CARD#positive", "Thẻ ATM rất tiện lợi khi sử dụng"),
-        ("INTERNET_BANKING#negative", "Internet banking hay bị lỗi"),
-        ("INTERNET_BANKING#positive", "Ứng dụng ngân hàng điện tử dễ sử dụng"),
-        ("MONEY_TRANSFER#negative", "Phí chuyển tiền quá đắt"),
-        ("PROMOTION#positive", "Chương trình khuyến mãi rất hấp dẫn"),
-        ("SECURITY#positive", "Bảo mật tài khoản rất tốt")
-    ]
-
-    print("Testing Vietnamese banking aspect sentiment analysis:")
     print("-" * 60)
 
-    for expected_aspect_sentiment, text in examples:
+    for expected_label, text in examples:
         try:
             prediction, confidence, top_predictions = predict_text(model, text)
 
             if prediction:
                 print(f"Text: {text}")
-                print(f"Expected: {expected_aspect_sentiment}")
+                print(f"Expected: {expected_label}")
                 print(f"Predicted: {prediction}")
                 print(f"Confidence: {confidence:.3f}")
 
@@ -102,12 +131,17 @@ def predict_banking_examples(model):
             print("-" * 60)
 
 
-def interactive_mode(model):
-    """Interactive mode for testing custom banking text"""
+def interactive_mode(model, model_type):
+    """Interactive mode for testing custom text"""
     print("\n" + "="*60)
-    print("INTERACTIVE MODE - VIETNAMESE BANKING ASPECT SENTIMENT ANALYSIS")
-    print("="*60)
-    print("Enter Vietnamese banking text to analyze aspect and sentiment (type 'quit' to exit):")
+    if model_type == "vlsp2016":
+        print("INTERACTIVE MODE - VIETNAMESE GENERAL SENTIMENT ANALYSIS")
+        print("="*60)
+        print("Enter Vietnamese text to analyze sentiment (type 'quit' to exit):")
+    else:
+        print("INTERACTIVE MODE - VIETNAMESE BANKING ASPECT SENTIMENT ANALYSIS")
+        print("="*60)
+        print("Enter Vietnamese banking text to analyze aspect and sentiment (type 'quit' to exit):")
 
     while True:
         try:
@@ -122,7 +156,10 @@ def interactive_mode(model):
             prediction, confidence, top_predictions = predict_text(model, user_input)
 
             if prediction:
-                print(f"Predicted aspect-sentiment: {prediction}")
+                if model_type == "vlsp2016":
+                    print(f"Predicted sentiment: {prediction}")
+                else:
+                    print(f"Predicted aspect-sentiment: {prediction}")
                 print(f"Confidence: {confidence:.3f}")
 
                 # Show top 3 predictions
@@ -145,25 +182,35 @@ def simple_usage_examples():
 
     print("Code examples:")
     print("""
-# Pulse Core 1 Model (Vietnamese Banking Aspect Sentiment Analysis)
+# Pulse Core 1 Models (Vietnamese Sentiment Analysis)
 from huggingface_hub import hf_hub_download
 import joblib
 
-# Download and load Pulse Core 1 model from HuggingFace Hub
-model = joblib.load(
+# Option 1: General Sentiment Analysis (VLSP2016)
+general_model = joblib.load(
+    hf_hub_download("undertheseanlp/pulse_core_1", "vlsp2016_sentiment_20250929_075529.joblib")
+)
+
+# Make prediction on general text
+general_text = "Sản phẩm này rất tốt"
+prediction = general_model.predict([general_text])[0]
+print(f"Sentiment: {prediction}")
+
+# Option 2: Banking Aspect Sentiment Analysis (UTS2017_Bank)
+banking_model = joblib.load(
     hf_hub_download("undertheseanlp/pulse_core_1", "uts2017_sentiment_20250928_131716.joblib")
 )
 
 # Make prediction on banking text
 bank_text = "Tôi muốn mở tài khoản tiết kiệm"
-prediction = model.predict([bank_text])[0]
+prediction = banking_model.predict([bank_text])[0]
 print(f"Aspect-Sentiment: {prediction}")
 
 # For detailed predictions with confidence scores
-probabilities = model.predict_proba([bank_text])[0]
+probabilities = banking_model.predict_proba([bank_text])[0]
 top_indices = probabilities.argsort()[-3:][::-1]
 for idx in top_indices:
-    category = model.classes_[idx]
+    category = banking_model.classes_[idx]
     prob = probabilities[idx]
     print(f"{category}: {prob:.3f}")
 
@@ -173,48 +220,63 @@ for idx in top_indices:
 
 def main():
     """Main demonstration function"""
-    print("Pulse Core 1 - Vietnamese Banking Aspect Sentiment Analysis")
+    print("Pulse Core 1 - Vietnamese Sentiment Analysis System")
     print("=" * 60)
 
     try:
         # Show simple usage examples
         simple_usage_examples()
 
-        # Test banking aspect sentiment model
+        # Test both models
         print("\n" + "="*60)
-        print("TESTING PULSE CORE 1 MODEL (Vietnamese Banking Aspect Sentiment Analysis)")
+        print("TESTING PULSE CORE 1 MODELS")
         print("="*60)
 
-        model = load_model_from_hub()
-        predict_banking_examples(model)
+        # Test VLSP2016 general sentiment model
+        print("\n1. Testing VLSP2016 General Sentiment Model")
+        print("-" * 40)
+        vlsp_model, vlsp_type = load_model_from_hub("vlsp2016")
+        predict_sentiment_examples(vlsp_model, vlsp_type)
+
+        # Test UTS2017 banking aspect sentiment model
+        print("\n2. Testing UTS2017 Banking Aspect Sentiment Model")
+        print("-" * 40)
+        uts_model, uts_type = load_model_from_hub("uts2017")
+        predict_sentiment_examples(uts_model, uts_type)
 
         # Check if we're in an interactive environment
         try:
             import sys
             if hasattr(sys, 'ps1') or sys.stdin.isatty():
-                choice = input("\nEnter interactive mode for banking aspect sentiment analysis? (y/n): ").strip().lower()
+                choice = input("\nEnter interactive mode? Choose model type (vlsp2016/uts2017/n): ").strip().lower()
 
-                if choice in ['y', 'yes']:
-                    interactive_mode(model)
+                if choice == 'vlsp2016':
+                    interactive_mode(vlsp_model, "vlsp2016")
+                elif choice == 'uts2017':
+                    interactive_mode(uts_model, "uts2017")
 
         except (EOFError, OSError):
             print("\nInteractive mode not available in this environment.")
             print("Run this script in a regular terminal to use interactive mode.")
 
         print("\nDemonstration complete!")
-        print("\nPulse Core 1 model is available on Hugging Face Hub:")
+        print("\nPulse Core 1 models are available on Hugging Face Hub:")
         print("- Repository: undertheseanlp/pulse_core_1")
-        print("- Model file: uts2017_sentiment_20250928_131716.joblib")
-        print("- Task: Vietnamese Banking Aspect Sentiment Analysis")
-        print("- Classes: 35 aspect-sentiment combinations")
+        print("- VLSP2016 Model: vlsp2016_sentiment_20250929_075529.joblib")
+        print("  * Task: Vietnamese General Sentiment Analysis")
+        print("  * Classes: 3 sentiment polarities")
+        print("  * Test accuracy: 71.14%")
+        print("- UTS2017 Model: uts2017_sentiment_20250928_131716.joblib")
+        print("  * Task: Vietnamese Banking Aspect Sentiment Analysis")
+        print("  * Classes: 35 aspect-sentiment combinations")
+        print("  * Test accuracy: 71.72%")
         print("- Model type: Support Vector Classification (SVC)")
-        print("- Test accuracy: 71.72%")
 
     except ImportError:
         print("Error: huggingface_hub is required. Install with:")
         print("  pip install huggingface_hub")
     except Exception as e:
-        print(f"Error loading model: {e}")
+        print(f"Error loading models: {e}")
         print("\nMake sure you have internet connection and try again.")