Update app.py

app.py

@@ -57,16 +57,17 @@ def analyze_article(text: str) -> dict:
     
     Keys to return:
     "sentiment_score": A float between -1.0 (highly negative) and 1.0 (highly positive).
-    "primary_tone": The single dominant emotion (e.g., anger, fear, joy, sadness, surprise, neutral).
+    "primary_tone": The single dominant emotion.
     "primary_theme": Choose ONE from: ["economic consequences", "moral and ethical fairness", "legal and bureaucratic", "public safety and health"].
-    "tone_scores": A dictionary scoring the top 3 emotions present from 0.0 to 1.0 (e.g., {{"fear": 0.8, "anger": 0.5}}).
+    "tone_scores": A dictionary scoring THESE EXACT 6 EMOTIONS from 0.0 to 1.0: {{"anger": 0.0, "fear": 0.0, "joy": 0.0, "sadness": 0.0, "surprise": 0.0, "trust": 0.0}}.
+    "framing_words": A list of the 5 to 8 most emotionally charged, biased, or subjective words used in the text (e.g., ["draconian", "slammed", "titans", "catastrophic"]).
     
     Text to analyze:
     "{safe_text}"
     """
     
     messages = [{"role": "user", "content": prompt}]
-    response = client.chat_completion(messages=messages, max_tokens=250, temperature=0.1)
+    response = client.chat_completion(messages=messages, max_tokens=300, temperature=0.1)
     response_text = response.choices[0].message.content
     llm_data = _extract_json_from_llm(response_text)
 
@@ -77,7 +78,8 @@ def analyze_article(text: str) -> dict:
         "sentiment_score": llm_data.get("sentiment_score", 0.0),
         "primary_tone": llm_data.get("primary_tone", "neutral"),
         "primary_theme": llm_data.get("primary_theme", "unclear"),
-        "tone_scores": llm_data.get("tone_scores", {"neutral": 1.0}),
+        "tone_scores": llm_data.get("tone_scores", {"anger": 0, "fear": 0, "joy": 0, "sadness": 0, "surprise": 0, "trust": 0}),
+        "framing_words": llm_data.get("framing_words", []),
         "subjectivity_score": subjectivity_score,
         "reading_ease": max(0.0, min(100.0, raw_reading_ease)),
     }
@@ -146,29 +148,21 @@ def _create_comparison_radar_chart(results_a: dict, results_b: dict) -> go.Figur
     return fig
 
 
-def _highlight_framing_words(text: str) -> str:
-    """Highlights subjective or emotional words in the text snippet."""
-    raw_sentences = re.split(r'(?<=[.!?]) +', text)
-    snippet = " ".join(raw_sentences[:3])
-    if not snippet:
+def _highlight_framing_words(text: str, target_words: list) -> str:
+    """Highlights LLM-identified framing words in the full text snippet."""
+    if not text:
         return ""
 
-    blob = TextBlob(snippet)
-    target_words = set()
+    words = text.split()    
+    highlighted_text = display_text
     
-    for word in blob.words:
-        w_sentiment = TextBlob(word).sentiment 
-        if w_sentiment.subjectivity > 0.5 or abs(w_sentiment.polarity) > 0.3:
-            if len(word) > 2: 
-                target_words.add(str(word))
-                
-    highlighted_snippet = snippet
     for word in target_words:
-        pattern = r'\b(' + re.escape(word) + r')\b'
-        replacement = r"<span style='background-color: #fef08a; color: #854d0e; font-weight: 600; padding: 0.1rem 0.2rem; border-radius: 4px;'>\1</span>"
-        highlighted_snippet = re.sub(pattern, replacement, highlighted_snippet, flags=re.IGNORECASE)
+        if len(word) > 2: 
+            pattern = r'\b(' + re.escape(word) + r')\b'
+            replacement = r"<span style='background-color: #fef08a; color: #854d0e; font-weight: 600; padding: 0.1rem 0.2rem; border-radius: 4px;'>\1</span>"
+            highlighted_text = re.sub(pattern, replacement, highlighted_text, flags=re.IGNORECASE)
 
-    return highlighted_snippet + ("..." if len(raw_sentences) > 3 else "")
+    return highlighted_text
 
 @st.cache_data(ttl=3600, show_spinner=False)
 def fetch_article_text(url: str) -> str:
@@ -351,7 +345,7 @@ if st.session_state.results_a and st.session_state.results_b:
         st.plotly_chart(_create_sentiment_gauge(r_a["sentiment_score"], "Sentiment Bias"), use_container_width=True, key="gauge_a")
 
         st.markdown("**Key Framing Language:**")
-        annotated_text = _highlight_framing_words(user_article_a)
+        annotated_text = _highlight_framing_words(user_article_a, r_a['framing_words'])
         st.markdown(f"<div style='background-color: #f8fafc; padding: 1rem; border-radius: 8px; border: 1px solid #e2e8f0;'>{annotated_text}</div>", unsafe_allow_html=True)
 
     # Render Column B
@@ -368,5 +362,5 @@ if st.session_state.results_a and st.session_state.results_b:
         st.plotly_chart(_create_sentiment_gauge(r_b["sentiment_score"], "Sentiment Bias"), use_container_width=True, key="gauge_b")
 
         st.markdown("**Key Framing Language:**")
-        annotated_text = _highlight_framing_words(user_article_b)
+        annotated_text = _highlight_framing_words(user_article_b, r_b['framing_words'])
         st.markdown(f"<div style='background-color: #f8fafc; padding: 1rem; border-radius: 8px; border: 1px solid #e2e8f0;'>{annotated_text}</div>", unsafe_allow_html=True)