Create pages/1_Data_Overview.py

pages/1_Data_Overview.py

@@ -0,0 +1,50 @@
+import streamlit as st
+
+st.title("📊 Data Collection & Preprocessing")
+
+st.markdown("""
+
+🔍 **YouTube Comment Extraction**
+
+✅ Used **YouTube Data API v3** via the **requests** library and **API Key** authentication
+
+📹 Extracted comments from 150+ video IDs across balanced sentiment categories:
+
+🟢 **Positive:** "heartwarming reunion", "feel good moments"
+
+🔴 **Negative:** "controversial incident", "bad customer experience"
+
+⚪ **Neutral:** "tech reviews", "travel vlogs"
+
+
+📈 Gathered over **15,000** top-level comments using pagination (nextPageToken)
+
+💾 Data saved into a **JSON** format with keys: **video_id** and **comment**
+
+
+
+---
+
+🧹 **Text Preprocessing Steps**
+
+✅ Removed HTML tags, emojis, special characters, and links
+
+🔡 Converted text to lowercase
+
+🧽 Removed stopwords and non-alphabetic tokens
+
+🧠 Applied **tokenization**
+
+
+The cleaned text was used to train our **sentiment classifier** in the next step.
+
+
+---
+
+""")
+
+if st.button("Next"):
+    st.switch_page("pages/2_Model_Training.py")
+
+if st.button("Go to Home"):
+    st.switch_page("app.py")