Update app.py

app.py

@@ -2,9 +2,8 @@
 Hotel Review Analysis System for The Kimberley Hotel Hong Kong
 ISOM5240 Group Project
 
-This Streamlit application analyzes guest reviews in multiple languages, performs sentiment
+Automatically analyzes guest reviews in multiple languages, performs sentiment
 analysis and aspect detection, then generates professional responses.
-
 """
 
 import streamlit as st
@@ -15,14 +14,12 @@ from transformers import (
 )
 import torch
 import re
-import pyperclip
 from langdetect import detect
 
 # ===== CONSTANTS =====
-MAX_CHARS = 500  # Strict character limit for reviews as per requirements
+MAX_CHARS = 500  # Character limit for reviews
 
 # Supported languages with their display names
-# Note: Chinese model handles both Mandarin and Cantonese text
 SUPPORTED_LANGUAGES = {
     'en': 'English',
     'zh': 'Chinese',
@@ -33,70 +30,50 @@ SUPPORTED_LANGUAGES = {
 }
 
 # ===== ASPECT CONFIGURATION =====
-# Dictionary mapping aspect categories to their keywords
-# Used for both keyword matching and zero-shot classification
 aspect_map = {
-    # Location related aspects
+    # Location
     "location": ["location", "near", "close", "access", "transport", "distance", "area", "tsim sha tsui", "kowloon"],
     "view": ["view", "scenery", "vista", "panorama", "outlook", "skyline"],
-    "parking": ["parking", "valet", "garage", "car park", "vehicle"],
-
-    # Room related aspects
-    "room comfort": ["comfortable", "bed", "pillows", "mattress", "linens", "cozy", "hard", "soft"],
-    "room cleanliness": ["clean", "dirty", "spotless", "stains", "hygiene", "sanitation", "dusty"],
-    "room amenities": ["amenities", "minibar", "coffee", "tea", "fridge", "facilities", "tv", "kettle"],
-    "bathroom": ["bathroom", "shower", "toilet", "sink", "towel", "faucet", "toiletries"],
-
-    # Service related aspects
-    "staff service": ["staff", "friendly", "helpful", "rude", "welcoming", "employee", "manager"],
-    "reception": ["reception", "check-in", "check-out", "front desk", "welcome", "registration"],
-    "housekeeping": ["housekeeping", "maid", "cleaning", "towels", "service", "turndown"],
-    "concierge": ["concierge", "recommendation", "advice", "tips", "guidance", "directions"],
-    "room service": ["room service", "food delivery", "order", "meal", "tray"],
-
-    # Facilities aspects
-    "dining": ["breakfast", "dinner", "restaurant", "meal", "food", "buffet", "lunch"],
-    "bar": ["bar", "drinks", "cocktail", "wine", "lounge", "happy hour"],
-    "pool": ["pool", "swimming", "jacuzzi", "sun lounger", "deck", "towels"],
-    "spa": ["spa", "massage", "treatment", "relax", "wellness", "sauna"],
-    "fitness": ["gym", "fitness", "exercise", "workout", "training", "weights"],
-
-    # Technical aspects
-    "Wi-Fi": ["wifi", "internet", "connection", "online", "network", "speed"],
-    "AC": ["air conditioning", "AC", "temperature", "heating", "cooling", "ventilation"],
-    "elevator": ["elevator", "lift", "escalator", "vertical transport", "wait"],
-
-    # Value aspects
-    "pricing": ["price", "expensive", "cheap", "value", "rate", "cost", "worth"],
-    "extra charges": ["charge", "fee", "bill", "surcharge", "additional", "hidden"]
+    
+    # Room
+    "room comfort": ["comfortable", "bed", "pillows", "mattress", "linens", "cozy"],
+    "room cleanliness": ["clean", "dirty", "spotless", "stains", "hygiene"],
+    
+    # Service
+    "staff service": ["staff", "friendly", "helpful", "rude", "welcoming"],
+    "reception": ["reception", "check-in", "check-out", "front desk"],
+    
+    # Facilities
+    "dining": ["breakfast", "dinner", "restaurant", "meal", "food"],
+    "spa": ["spa", "massage", "treatment", "relax"],
+    
+    # Technical
+    "Wi-Fi": ["wifi", "internet", "connection"],
+    "AC": ["air conditioning", "AC", "temperature"]
 }
 
-# Pre-defined professional responses for positive aspects
 aspect_responses = {
-    "location": "We're delighted you enjoyed our prime location in the heart of Tsim Sha Tsui.",
+    "location": "We're delighted you enjoyed our prime location in Tsim Sha Tsui.",
     "view": "It's wonderful to hear you appreciated the views from your room.",
-    "room comfort": "Our team takes special care to ensure room comfort for all guests.",
-    # ... (other responses remain unchanged)
+    "room comfort": "Our team takes special care to ensure room comfort.",
+    "room cleanliness": "Your comments about cleanliness have been noted.",
+    "staff service": "Your feedback about our staff has been shared with the team.",
+    "dining": "We appreciate your comments about our dining options."
 }
 
-# Improvement actions for negative aspects
 improvement_actions = {
     "AC": "have addressed the air conditioning issues",
     "housekeeping": "have reviewed our cleaning procedures",
-    # ... (other actions remain unchanged)
+    "Wi-Fi": "are upgrading our network infrastructure"
 }
 
 # ===== MODEL CONFIGURATION =====
-# Helsinki-NLP translation models for supported language pairs
 TRANSLATION_MODELS = {
-    # Translations to English (for analysis)
-    'zh-en': 'Helsinki-NLP/opus-mt-zh-en',    # Chinese
-    'ja-en': 'Helsinki-NLP/opus-mt-ja-en',    # Japanese
-    'ko-en': 'Helsinki-NLP/opus-mt-ko-en',    # Korean
-    'fr-en': 'Helsinki-NLP/opus-mt-fr-en',    # French
-    'de-en': 'Helsinki-NLP/opus-mt-de-en',    # German
-    
-    # Translations from English (for responses)
+    'zh-en': 'Helsinki-NLP/opus-mt-zh-en',
+    'ja-en': 'Helsinki-NLP/opus-mt-ja-en',
+    'ko-en': 'Helsinki-NLP/opus-mt-ko-en',
+    'fr-en': 'Helsinki-NLP/opus-mt-fr-en',
+    'de-en': 'Helsinki-NLP/opus-mt-de-en',
     'en-zh': 'Helsinki-NLP/opus-mt-en-zh',
     'en-ja': 'Helsinki-NLP/opus-mt-en-ja',
     'en-ko': 'Helsinki-NLP/opus-mt-en-ko',
@@ -104,82 +81,43 @@ TRANSLATION_MODELS = {
     'en-de': 'Helsinki-NLP/opus-mt-en-de'
 }
 
-# ===== MODEL LOADING FUNCTIONS =====
+# ===== MODEL LOADING =====
 @st.cache_resource
 def load_sentiment_model():
-    """
-    Load and cache the fine-tuned sentiment analysis model.
-    Uses a BERTweet model fine-tuned on hotel reviews.
-    Returns:
-        tuple: (model, tokenizer)
-    """
     model = AutoModelForSequenceClassification.from_pretrained("smtsead/fine_tuned_bertweet_hotel")
     tokenizer = AutoTokenizer.from_pretrained('finiteautomata/bertweet-base-sentiment-analysis')
     return model, tokenizer
 
 @st.cache_resource
 def load_aspect_classifier():
-    """
-    Load and cache the zero-shot aspect classifier.
-    Uses DeBERTa model for multi-label aspect classification.
-    Returns:
-        pipeline: Zero-shot classification pipeline
-    """
     return pipeline("zero-shot-classification", model="MoritzLaurer/deberta-v3-base-zeroshot-v1.1-all-33")
 
 @st.cache_resource
 def load_translation_model(src_lang, target_lang='en'):
-    """
-    Load and cache the appropriate Helsinki-NLP translation model.
-    Args:
-        src_lang (str): Source language code
-        target_lang (str): Target language code (default 'en')
-    Returns:
-        pipeline: Translation pipeline
-    Raises:
-        ValueError: If language pair is not supported
-    """
     model_key = f"{src_lang}-{target_lang}"
     if model_key not in TRANSLATION_MODELS:
         raise ValueError(f"Unsupported translation: {src_lang}→{target_lang}")
     return pipeline("translation", model=TRANSLATION_MODELS[model_key])
 
 # ===== CORE FUNCTIONS =====
+def detect_language(text):
+    try:
+        lang = detect(text)
+        return 'zh' if lang in ['zh', 'yue'] else lang if lang in SUPPORTED_LANGUAGES else 'en'
+    except:
+        return 'en'
+
 def translate_text(text, src_lang, target_lang='en'):
-    """
-    Translate text between supported languages using Helsinki-NLP models.
-    Args:
-        text (str): Text to translate
-        src_lang (str): Source language code
-        target_lang (str): Target language code (default 'en')
-    Returns:
-        dict: Translation results or error message
-    """
     try:
         if src_lang == target_lang:
             return {'translation': text, 'source_lang': src_lang}
-            
         translator = load_translation_model(src_lang, target_lang)
         result = translator(text)[0]['translation_text']
-        return {
-            'original': text,
-            'translation': result,
-            'source_lang': src_lang,
-            'target_lang': target_lang
-        }
+        return {'translation': result, 'source_lang': src_lang}
     except Exception as e:
         return {'error': str(e)}
 
 def analyze_sentiment(text, model, tokenizer):
-    """
-    Perform sentiment analysis on text.
-    Args:
-        text (str): Text to analyze
-        model: Pretrained sentiment model
-        tokenizer: Corresponding tokenizer
-    Returns:
-        dict: Sentiment analysis results (label, confidence, sentiment)
-    """
     inputs = tokenizer(text, padding=True, truncation=True, max_length=512, return_tensors='pt')
     with torch.no_grad():
         outputs = model(**inputs)
@@ -193,16 +131,6 @@ def analyze_sentiment(text, model, tokenizer):
     }
 
 def detect_aspects(text, aspect_classifier):
-    """
-    Detect hotel aspects mentioned in text using two-stage approach:
-    1. Keyword matching to identify potential aspects
-    2. Zero-shot classification to confirm and score aspects
-    Args:
-        text (str): Text to analyze
-        aspect_classifier: Zero-shot classification pipeline
-    Returns:
-        list: Detected aspects with confidence scores
-    """
     relevant_aspects = []
     text_lower = text.lower()
     for aspect, keywords in aspect_map.items():
@@ -216,21 +144,10 @@ def detect_aspects(text, aspect_classifier):
             multi_label=True,
             hypothesis_template="This review discusses the hotel's {}."
         )
-        return [(aspect, f"{score:.0%}") for aspect, score in 
-                zip(result['labels'], result['scores']) if score > 0.6]
+        return [(aspect, f"{score:.0%}") for aspect, score in zip(result['labels'], result['scores']) if score > 0.6]
     return []
 
 def generate_response(sentiment, aspects, original_text):
-    """
-    Generate professional response based on sentiment and aspects.
-    Args:
-        sentiment (dict): Sentiment analysis results
-        aspects (list): Detected aspects with scores
-        original_text (str): Original review text
-    Returns:
-        str: Generated response
-    """
-    # Personalization - extract guest name if mentioned
     guest_name = ""
     name_match = re.search(r"(Mr\.|Ms\.|Mrs\.)\s(\w+)", original_text, re.IGNORECASE)
     if name_match:
@@ -239,12 +156,11 @@ def generate_response(sentiment, aspects, original_text):
     if sentiment['label'] == 1:
         response = f"""Dear{guest_name if guest_name else ' Valued Guest'},
 
-Thank you for choosing The Kimberley Hotel Hong Kong and for sharing your feedback."""
+Thank you for choosing The Kimberley Hotel Hong Kong."""
         
-        # Add relevant aspect responses (limit to 2 most relevant)
         added_aspects = set()
         for aspect, _ in sorted(aspects, key=lambda x: float(x[1][:-1]), reverse=True):
-            if aspect in aspect_responses and aspect not in added_aspects:
+            if aspect in aspect_responses:
                 response += "\n\n" + aspect_responses[aspect]
                 added_aspects.add(aspect)
                 if len(added_aspects) >= 2:
@@ -254,209 +170,120 @@ Thank you for choosing The Kimberley Hotel Hong Kong and for sharing your feedba
     else:
         response = f"""Dear{guest_name if guest_name else ' Guest'},
 
-Thank you for your feedback. We appreciate you taking the time to share your experience."""
+Thank you for your feedback."""
         
-        # Add improvement actions (limit to 2 most relevant)
         added_improvements = set()
         for aspect, _ in sorted(aspects, key=lambda x: float(x[1][:-1]), reverse=True):
-            if aspect in improvement_actions and aspect not in added_improvements:
+            if aspect in improvement_actions:
                 response += f"\n\nRegarding your comments about the {aspect}, we {improvement_actions[aspect]}."
                 added_improvements.add(aspect)
                 if len(added_improvements) >= 2:
                     break
         
-        response += "\n\nPlease don't hesitate to contact us if we can be of further assistance.\n\nSincerely,"
+        response += "\n\nPlease contact us if we can assist further.\n\nSincerely,"
     
     return response + "\nSam Tse\nGuest Relations Manager\nThe Kimberley Hotel Hong Kong"
 
 # ===== STREAMLIT UI =====
 def main():
-    """Main application function for Streamlit interface"""
-    # Page configuration
     st.set_page_config(
         page_title="Kimberley Review Assistant",
         page_icon="🏨",
         layout="centered"
     )
     
-    # Custom CSS styling
     st.markdown("""
     <style>
-        /* Header styling */
-        .header {
-            color: #003366;
-            font-size: 28px;
-            font-weight: bold;
-            margin-bottom: 10px;
-        }
-        /* Subheader styling */
-        .subheader {
-            color: #666666;
-            font-size: 16px;
-            margin-bottom: 30px;
-        }
-        /* Language badge styling */
-        .badge {
-            background-color: #e6f2ff;
-            color: #003366;
-            padding: 3px 10px;
-            border-radius: 15px;
-            font-size: 14px;
-            display: inline-block;
-            margin: 0 5px 5px 0;
-        }
-        /* Character counter styling */
-        .char-counter {
-            font-size: 12px;
-            color: #666;
-            text-align: right;
-            margin-top: -15px;
-            margin-bottom: 15px;
-        }
-        /* Warning style for character limit */
-        .char-counter.warning {
-            color: #ff6b6b;
-        }
-        /* Result box styling */
-        .result-box {
-            border-left: 4px solid #003366;
-            padding: 15px;
-            background-color: #f9f9f9;
-            margin: 20px 0;
-            border-radius: 0 8px 8px 0;
-            white-space: pre-wrap;
-        }
-        /* Aspect badge styling */
-        .aspect-badge {
-            background-color: #e6f2ff;
-            color: #003366;
-            padding: 2px 8px;
-            border-radius: 4px;
-            font-size: 14px;
-            display: inline-block;
-            margin: 2px;
-        }
+        .header { color: #003366; font-size: 28px; font-weight: bold; margin-bottom: 10px; }
+        .subheader { color: #666666; font-size: 16px; margin-bottom: 30px; }
+        .char-counter { font-size: 12px; color: #666; text-align: right; margin-top: -15px; }
+        .char-counter.warning { color: #ff6b6b; }
+        .result-box { border-left: 4px solid #003366; padding: 15px; background-color: #f9f9f9; margin: 20px 0; }
     </style>
     """, unsafe_allow_html=True)
     
-    # Application header
     st.markdown('<div class="header">The Kimberley Hotel Hong Kong</div>', unsafe_allow_html=True)
     st.markdown('<div class="subheader">Guest Review Analysis System</div>', unsafe_allow_html=True)
     
-    # Supported languages display
-    st.markdown("**Supported Review Languages:**")
-    lang_cols = st.columns(6)
-    for i, (code, name) in enumerate(SUPPORTED_LANGUAGES.items()):
-        lang_cols[i%6].markdown(f'<div class="badge">{name}</div>', unsafe_allow_html=True)
-    
-    # Language selection dropdown
-    review_lang = st.selectbox(
-        "Select review language:",
-        options=list(SUPPORTED_LANGUAGES.keys()),
-        format_func=lambda x: SUPPORTED_LANGUAGES[x],
-        index=0
-    )
-    
-    # Review input with character counter
     review = st.text_area("**Paste Guest Review:**", 
                          height=200,
                          max_chars=MAX_CHARS,
-                         placeholder=f"Enter review in any supported language (max {MAX_CHARS} characters)...",
+                         placeholder=f"Enter review (max {MAX_CHARS} characters)...",
                          key="review_input")
     
-    # Character counter logic
     char_count = len(st.session_state.review_input) if 'review_input' in st.session_state else 0
-    char_class = "warning" if char_count > MAX_CHARS else ""
-    st.markdown(f'<div class="char-counter {char_class}">{char_count}/{MAX_CHARS} characters</div>', 
+    st.markdown(f'<div class="char-counter{" warning" if char_count > MAX_CHARS else ""}">{char_count}/{MAX_CHARS} characters</div>', 
                 unsafe_allow_html=True)
     
-    # Main analysis button
     if st.button("Analyze & Generate Response", type="primary"):
         if not review.strip():
             st.error("Please enter a review")
             return
         
-        # Enforce character limit
         if char_count > MAX_CHARS:
-            st.warning(f"Review truncated to {MAX_CHARS} characters for analysis")
+            st.warning(f"Review truncated to {MAX_CHARS} characters")
             review = review[:MAX_CHARS]
         
         with st.spinner("Analyzing feedback..."):
             try:
-                # Translation to English if needed
+                # Auto-detect language
+                review_lang = detect_language(review)
+                st.info(f"Detected language: {SUPPORTED_LANGUAGES.get(review_lang, 'English')}")
+                
+                # Translate if not English
                 if review_lang != 'en':
                     translation = translate_text(review, review_lang, 'en')
                     if 'error' in translation:
                         st.error(f"Translation error: {translation['error']}")
                         return
                     analysis_text = translation['translation']
+                    
+                    with st.expander("View Translation"):
+                        st.write("**Original Review:**")
+                        st.write(review)
+                        st.write("**English Translation:**")
+                        st.write(translation['translation'])
                 else:
                     analysis_text = review
                 
-                # Load models
+                # Analyze text
                 sentiment_model, tokenizer = load_sentiment_model()
                 aspect_classifier = load_aspect_classifier()
                 
-                # Perform analysis
                 sentiment = analyze_sentiment(analysis_text, sentiment_model, tokenizer)
                 aspects = detect_aspects(analysis_text, aspect_classifier)
                 response = generate_response(sentiment, aspects, analysis_text)
                 
-                # Translate response back to original language if needed
+                # Translate response back if needed
                 if review_lang != 'en':
                     translation_back = translate_text(response, 'en', review_lang)
-                    if 'error' not in translation_back:
-                        final_response = translation_back['translation']
-                    else:
-                        st.warning(f"Couldn't translate response back: {translation_back['error']}")
-                        final_response = response
+                    final_response = translation_back['translation'] if 'error' not in translation_back else response
                 else:
                     final_response = response
                 
-                # Store results in session state
-                st.session_state.analysis_results = {
-                    'sentiment': sentiment,
-                    'aspects': aspects,
-                    'response': final_response,
-                    'original_lang': review_lang
-                }
-                
                 # Display results
                 st.divider()
                 
-                # Sentiment analysis results
                 col1, col2 = st.columns(2)
                 with col1:
                     st.markdown("### Sentiment Analysis")
-                    sentiment_icon = "✅" if sentiment['label'] == 1 else "⚠️"
-                    st.markdown(f"{sentiment_icon} **{sentiment['sentiment']}**")
-                    st.caption(f"Confidence level: {sentiment['confidence']}")
+                    st.markdown(f"{'✅' if sentiment['label'] == 1 else '⚠️'} **{sentiment['sentiment']}**")
+                    st.caption(f"Confidence: {sentiment['confidence']}")
                 
-                # Detected aspects
                 with col2:
-                    st.markdown("### Key Aspects Detected")
+                    st.markdown("### Key Aspects")
                     if aspects:
                         for aspect, score in sorted(aspects, key=lambda x: float(x[1][:-1]), reverse=True):
-                            st.markdown(f'<div class="aspect-badge">{aspect} ({score})</div>', unsafe_allow_html=True)
+                            st.markdown(f"- {aspect} ({score})")
                     else:
                         st.markdown("_No specific aspects detected_")
                 
-                # Generated response
                 st.divider()
                 st.markdown("### Draft Response")
                 st.markdown(f'<div class="result-box">{final_response}</div>', unsafe_allow_html=True)
                 
-                # Clipboard copy functionality
-                if st.button("Copy Response to Clipboard"):
-                    try:
-                        pyperclip.copy(final_response)
-                        st.success("Response copied to clipboard!")
-                    except Exception as e:
-                        st.error(f"Could not copy to clipboard: {e}")
-            
             except Exception as e:
-                st.error(f"An error occurred during analysis: {str(e)}")
+                st.error(f"An error occurred: {str(e)}")
 
-# Entry point
 if __name__ == "__main__":
     main()