Update app.py

app.py

@@ -1,30 +1,25 @@
 import gradio as gr
 from transformers import pipeline
 
-# Load fake news classifier
-classifier = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-fake-news", return_all_scores=True)
+# Use a valid public model
+classifier = pipeline("text-classification", model="michiyasunaga/BERT-fake-news-detection")
 
 def detect_fake_news(text):
-    results = classifier(text)[0]
-    results = sorted(results, key=lambda x: x['score'], reverse=True)
-
-    label = results[0]['label']
-    confidence = results[0]['score']
-
-    explanation = f"This article is classified as **{label.upper()}** with a confidence of **{confidence*100:.2f}%**.\n\n"
-    explanation += "### Full Scores:\n"
-    for r in results:
-        explanation += f"- {r['label']}: {r['score']*100:.2f}%\n"
+    result = classifier(text)[0]
+    label = result['label']
+    score = result['score']
     
+    explanation = (
+        f"The model predicts this news is **{label}** "
+        f"with a confidence of **{score:.2f}**.\n\n"
+        "🧠 This is based on BERT fine-tuned on a fake news dataset."
+    )
     return explanation
 
-# Gradio Interface
-demo = gr.Interface(
-    fn=detect_fake_news,
-    inputs=gr.Textbox(lines=12, placeholder="Paste your news article here...", label="📰 News Article"),
-    outputs=gr.Markdown(label="🧠 Fake News Analysis"),
-    title="🕵️‍♀️ Fake News Detector",
-    description="Paste a news article. This app will classify it as FAKE or REAL using a BERT-based model."
-)
+demo = gr.Interface(fn=detect_fake_news,
+                    inputs=gr.Textbox(lines=10, placeholder="Paste your news article here..."),
+                    outputs="markdown",
+                    title="🕵️ Fake News Detector",
+                    description="An NLP app that predicts whether a news article is fake or real using BERT.")
 
 demo.launch()