added label explanation

app.py

@@ -16,15 +16,26 @@ st.write("Enter a text and select a pre-trained model to get the sentiment analy
 text = st.text_input("Enter your text:")
 
 # Model selection
-model_options = [
-    "distilbert-base-uncased-finetuned-sst-2-english",
-    "textattack/bert-base-uncased-SST-2",
-    "cardiffnlp/twitter-roberta-base-sentiment",
-    "nlptown/bert-base-multilingual-uncased-sentiment"
-]
-
+model_options = {
+    "distilbert-base-uncased-finetuned-sst-2-english": {
+        "labels": ["NEGATIVE", "POSITIVE"],
+        "description": "This model classifies text into positive or negative sentiment. It is based on DistilBERT and fine-tuned on the Stanford Sentiment Treebank (SST-2) dataset.",
+    },
+    "textattack/bert-base-uncased-SST-2": {
+        "labels": ["LABEL_0", "LABEL_1"],
+        "description": "This model classifies text into positive(LABEL_1) or negative(LABEL_0) sentiment. It is based on BERT and fine-tuned on the Stanford Sentiment Treebank (SST-2) dataset.",
+    },
+    "cardiffnlp/twitter-roberta-base-sentiment": {
+        "labels": ["LABEL_0", "LABEL_1", "LABEL_2"],
+        "description": "This model classifies tweets into negative (LABEL_0), neutral(LABEL_1), or positive(LABEL_2) sentiment. It is based on RoBERTa and fine-tuned on a large dataset of tweets.",
+    },
+}
 selected_model = st.selectbox("Choose a pre-trained model:", model_options)
 
+st.write("### Model Information")
+st.write(f"**Labels:** {', '.join(model_options[selected_model]['labels'])}")
+st.write(f"**Description:** {model_options[selected_model]['description']}")
+
 # Load the model and perform sentiment analysis
 if st.button("Analyze"):
     if not text:
@@ -36,7 +47,7 @@ if st.button("Analyze"):
             st.write(f"Sentiment: {result[0]['label']} (confidence: {result[0]['score']:.2f})")
             if result[0]['label'] == 'POSITIVE':
                 st.balloons()
-            elif result[0]['label']== 'NEGATIVE' and result[0]['score']> 0.9:
+            elif result[0]['label'] in ['NEGATIVE', 'LABEL_0'] and result[0]['score']> 0.9:
                 st.error("Hater detected.")
 else:
     st.write("Enter a text and click 'Analyze' to perform sentiment analysis.")