Update app.py

app.py

@@ -33,11 +33,6 @@ def _load_nlp_models() -> typing.Dict[str, typing.Any]:
         model="SamLowe/roberta-base-go_emotions",
         top_k=5
     )
-    ner_extractor = pipeline(
-        "ner",
-        model="dslim/bert-base-NER",
-        aggregation_strategy="simple"
-    )
     nli_classifier = pipeline(
         "text-classification", 
         model="MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli" 
@@ -50,7 +45,6 @@ def _load_nlp_models() -> typing.Dict[str, typing.Any]:
     return {
         "sentiment": sentiment_analyzer,
         "emotion": emotion_classifier,
-        "ner": ner_extractor,
         "nli": nli_classifier,
         "theme": theme_classifier,
     }
@@ -99,11 +93,7 @@ def analyze_article(text: str) -> dict:
     ]
     theme_result = models["theme"](safe_text, framing_dimensions)
     primary_theme = theme_result["labels"][0]
-
-    # Named Entity Recognition 
-    ner_results = models["ner"](safe_text)
-    extracted_entities = list(set([ent["word"] for ent in ner_results if ent["score"] > 0.6]))
-
+    
     # Subjectivity and Readability Analysis
     subjectivity_score = TextBlob(safe_text).sentiment.subjectivity
     raw_reading_ease = textstat.flesch_reading_ease(safe_text)
@@ -117,7 +107,6 @@ def analyze_article(text: str) -> dict:
         "primary_tone": primary_tone,
         "primary_theme": primary_theme,
         "tone_scores": tone_scores,
-        "entities": extracted_entities,
     }
 
 
@@ -184,23 +173,31 @@ def _create_comparison_radar_chart(results_a: dict, results_b: dict) -> go.Figur
     return fig
 
 
-def _highlight_subjective_sentences(text: str) -> str:
-    """Highlights subjective/opinionated sentences in the text."""
-    raw_sentences = text.replace("?", ".").replace("!", ".").split(".")
-    sentences = [s.strip() + "." for s in raw_sentences if len(s.strip()) > 20]
-    
-    scored_sentences = [(sentence, TextBlob(sentence).sentiment.subjectivity) for sentence in sentences]
-    
-    top_subjective = sorted(scored_sentences, key=lambda x: x[1], reverse=True)[:3]
-    top_sentences = [item[0] for item in top_subjective if item[1] > 0.3]
-    
-    if not top_sentences:
-        return text[:250] + "..."
-        
-    highlighted_text = " ... ".join(top_sentences)
-    return f"<span style='background-color: #e0e7ff; color: #3730a3; font-weight: 500; padding: 0.2rem 0.4rem; border-radius: 8px; font-size: 0.95em;'>{highlighted_text}</span>"
+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:
+        return ""
 
+    blob = TextBlob(snippet)
+    target_words = set()
+    
+    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)
+
+    return highlighted_snippet + ("..." if len(raw_sentences) > 3 else "")
 
+    
 def fetch_article_text(url: str) -> str:
     """Scrapes article text."""
     downloaded = trafilatura.fetch_url(url)
@@ -303,7 +300,7 @@ st.divider()
 with st.spinner("Starting NLP models."):
     _load_nlp_models()
 
-input_method = st.radio("Input Method", ["Paste Text", "Paste URL"], horizontal=True, index=1)
+input_method = st.radio("Input Method", ["Paste Text", "Paste URL"], horizontal=True, index=0)
 
 col1, col2 = st.columns(2)
 
@@ -372,9 +369,6 @@ if st.session_state.results_a and st.session_state.results_b:
         m4.metric("Reading Ease", f"{r_a['reading_ease']:.1f}")
 
         st.plotly_chart(_create_sentiment_gauge(r_a["sentiment_score"], "Sentiment Bias"), use_container_width=True, key="gauge_a")
-        
-        if r_a["entities"]:
-            st.markdown(f"**Extracted Entities:** `{', '.join(r_a['entities'])}`")
 
         st.markdown("**Key Framing Language:**")
         annotated_text = _highlight_subjective_sentences(user_article_a)
@@ -392,9 +386,6 @@ if st.session_state.results_a and st.session_state.results_b:
         m4.metric("Reading Ease", f"{r_b['reading_ease']:.1f}")
 
         st.plotly_chart(_create_sentiment_gauge(r_b["sentiment_score"], "Sentiment Bias"), use_container_width=True, key="gauge_b")
-        
-        if r_b["entities"]:
-            st.markdown(f"**Extracted Entities:** `{', '.join(r_b['entities'])}`")
 
         st.markdown("**Key Framing Language:**")
         annotated_text = _highlight_subjective_sentences(user_article_b)