Update app.py

app.py

@@ -41,47 +41,49 @@ def main():
         st.warning("Please enter a review to analyze.")
         return
 
-    # Sentiment & Keywords
+    # Load models
     sentiment_pipeline = load_sentiment_pipeline()
     kw_model = load_keybert_model()
 
+    # Run sentiment analysis
     scores = sentiment_pipeline(review)[0]
     sentiment_results = {item['label']: float(item['score']) for item in scores}
 
-    st.subheader("Sentiment Scores")
-    st.json({k: round(v, 4) for k, v in sentiment_results.items()})
+    # Display scores and keywords side by side
+    col1, col2 = st.columns(2)
+    with col1:
+        st.subheader("Sentiment Scores")
+        st.json({k: round(v, 4) for k, v in sentiment_results.items()})
+    with col2:
+        st.subheader("Top 3 Keywords")
+        keywords = kw_model.extract_keywords(
+            review,
+            keyphrase_ngram_range=(1, 2),
+            stop_words="english",
+            top_n=3
+        )
+        for kw, score in keywords:
+            st.write(f"• {kw} ({score:.4f})")
 
     # Bar chart of sentiment scores
     df_scores = pd.DataFrame.from_dict(sentiment_results, orient='index', columns=['score'])
     df_scores.index.name = 'label'
     st.bar_chart(df_scores)
 
-    # Highest sentiment
+    # Highlight highest sentiment without subheader
     max_label, max_score = max(sentiment_results.items(), key=lambda x: x[1])
-    st.subheader("Highest Sentiment")
     st.markdown(f"**Highest Sentiment:** **{max_label}** ({max_score:.4f})")
 
-    # Top 3 keywords
-    keywords = kw_model.extract_keywords(
-        review,
-        keyphrase_ngram_range=(1, 2),
-        stop_words="english",
-        top_n=3
-    )
-    st.subheader("Top 3 Keywords")
-    for kw, score in keywords:
-        st.write(f"• {kw} ({score:.4f})")
-
     # GPT-Driven Analysis & Suggestions (detailed)
     st.subheader("GPT Analysis & Seller Suggestions")
     prompt = f"""
 You are an analytical e-commerce feedback expert.
-Review: "{review}"
+Review: \"{review}\"
 Sentiment Scores: {sentiment_results}
 Top Keywords: {[kw for kw, _ in keywords]}
 Tasks:
 1. Write a concise paragraph (2 sentences) interpreting customer sentiment by combining the scores and keywords.
-2. Provide 3 actionable suggestions with brief explanations (up to 5 sentences each).
+2. Provide 3 actionable suggestions with brief explanations (up to 12 words each).
 """
 
     response = openai_client.chat.completions.create(