Update app.py

app.py

@@ -11,10 +11,10 @@ tokenizer = GPT2Tokenizer.from_pretrained(model_name)
 sentiment_analysis = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
 
 # Streamlit UI
-st.title("GPT-2 Movie Review Sentiment Analysis")
+st.title("GPT-2 Movie Sentiment Analysis")
 
 # Input text for sentiment analysis
-input_text = st.text_area("Enter movie review:", "")
+input_text = st.text_area("Enter movie sentiment:", "")
 
 # Choose analysis type
 analysis_type = st.radio("Select analysis type:", ["Zero-shot", "One-shot", "Few-shot"])
@@ -24,15 +24,20 @@ if st.button("Analyze Sentiment"):
     if analysis_type == "Zero-shot":
         results = sentiment_analysis(input_text)
     elif analysis_type == "One-shot":
-        prompt = "This movie review is about a "
-        input_text = prompt + input_text
-        results = sentiment_analysis(input_text)
+        # Use the input text as the single example
+        results = sentiment_analysis(f"This movie is about {input_text}")
     elif analysis_type == "Few-shot":
-        prompt = "This movie review is about a positive topic. " + input_text
-        results = sentiment_analysis(prompt)
+        # Use multiple examples for few-shot analysis
+        examples = [
+            f"This movie sets an example of bad ethics. {input_text}",
+            f"I loved this movie. {input_text}",
+            f"The movie is neither good nor bad. {input_text}"
+        ]
+        input_text = " ".join(examples)
+        results = sentiment_analysis(input_text)
 
     # Display results
     st.write("Sentiment:", results[0]['label'])
     st.write("Confidence:", results[0]['score'])
 
-# Note: This is a basic example, and you might need to fine-tune it based on your specific use case and requirements.
+# Note: This is a basic example, and you might need to fine-tune it based on your specific use case and requirements.