Update app.py

app.py

@@ -1,61 +1,85 @@
 import streamlit as st
 import pandas as pd
 import nltk
-from textblob import TextBlob
 import matplotlib.pyplot as plt
+import seaborn as sns
+from textblob import TextBlob
+from transformers import pipeline
 from wordcloud import WordCloud
+import os
 
 # Ensure necessary NLTK datasets are downloaded
 nltk.download('punkt')
 
+# Load pre-trained NLP model for classification
+classifier = pipeline("text-classification", model="distilbert-base-uncased-finetuned-sst-2-english")
+
 # Function to analyze sentiment
 def analyze_sentiment(text):
     analysis = TextBlob(text)
     return analysis.sentiment.polarity  # Returns sentiment score (-1 to 1)
 
-# Function to categorize microaggressions (basic NLP)
-def categorize_microaggression(text):
-    keywords = {
-        "Microinvalidation": ["you're overreacting", "stop being so sensitive", "I don’t see color"],
-        "Microinsult": ["you’re so articulate", "where are you really from", "you must be good at math"],
-        "Microassault": ["racial slur", "explicit insult", "offensive joke"]
-    }
-    
-    for category, phrases in keywords.items():
-        for phrase in phrases:
-            if phrase in text.lower():
-                return category
-    return "Uncategorized"
+# Function to categorize microaggressions using AI
+def classify_microaggression(text):
+    result = classifier(text)[0]
+    return result["label"], result["score"]
 
 # Streamlit UI
-st.title("MicroAggression Insight Tool")
-st.write("Analyze, categorize, and visualize reported microaggressions.")
+st.title("MicroAggression Insight Tool 🚀")
+st.write("Analyze, categorize, and visualize reported microaggressions using AI and psychological research methods.")
 
-# Collect user input
+# **Ethical Research Consent Notice**
+st.markdown("### Ethical Considerations")
+st.write("By submitting your responses, you agree to participate in this study anonymously. Your data will be stored securely for research purposes.")
+
+# **Experimental Study: Perception & Acceptability Ratings**
+st.subheader("Microaggression Perception Experiment")
+st.write("How acceptable do you find the following statement?")
+
+# User Input for Microaggression Statement
 user_input = st.text_area("Enter a microaggression example:")
 
+rating = st.slider("Rate on a scale of 1 (Not Acceptable) to 5 (Completely Acceptable)", 1, 5)
+emotional_impact = st.slider("How emotionally impactful is this? (1 = Not at all, 5 = Very Strong)", 1, 5)
+
 if st.button("Analyze"):
     if user_input:
         sentiment_score = analyze_sentiment(user_input)
-        category = categorize_microaggression(user_input)
+        category, confidence = classify_microaggression(user_input)
 
         # Display results
-        st.write(f"**Predicted Category:** {category}")
+        st.write(f"**Predicted Category:** {category} (Confidence: {confidence:.2f})")
         st.write(f"**Sentiment Score:** {sentiment_score:.2f} (Negative: -1, Neutral: 0, Positive: 1)")
+        st.write(f"**Perceived Acceptability:** {rating}/5")
+        st.write(f"**Emotional Impact:** {emotional_impact}/5")
 
         # Store input in a dataframe
-        df = pd.DataFrame({"Text": [user_input], "Category": [category], "Sentiment": [sentiment_score]})
+        df = pd.DataFrame([[user_input, category, sentiment_score, rating, emotional_impact]], 
+                          columns=["Text", "Category", "Sentiment", "Acceptability", "Impact"])
         
-        # Save locally (optional)
-        df.to_csv("data.csv", mode='a', header=False, index=False)
+        # Save data to CSV
+        file_path = "data.csv"
+        if not os.path.exists(file_path):
+            df.to_csv(file_path, index=False)
+        else:
+            df.to_csv(file_path, mode='a', header=False, index=False)
+
+# **Focus Group & Open-ended Research Input**
+st.subheader("📢 Focus Group: Share Your Perspective")
+response = st.text_area("Describe how this statement made you feel:")
+if st.button("Submit Response"):
+    if response:
+        with open("qualitative_responses.csv", "a") as f:
+            f.write(response + "\n")
+        st.success("Response recorded! ✅")
+
+# **Data Analysis & Visualization**
+st.subheader("📊 Data Insights & Visualizations")
 
-# Load existing data
 try:
-    data = pd.read_csv("data.csv", names=["Text", "Category", "Sentiment"])
+    data = pd.read_csv("data.csv")
     
     if not data.empty:
-        st.subheader("Data Insights")
-        
         # Show category distribution
         st.write("### Microaggression Category Distribution")
         category_counts = data["Category"].value_counts()
@@ -70,5 +94,23 @@ try:
         ax.imshow(wordcloud, interpolation="bilinear")
         ax.axis("off")
         st.pyplot(fig)
+
+        # **Correlation Heatmap**
+        st.write("### Correlation Between Sentiment, Acceptability, and Impact")
+        plt.figure(figsize=(6, 4))
+        sns.heatmap(data[["Sentiment", "Acceptability", "Impact"]].corr(), annot=True, cmap="coolwarm", fmt=".2f")
+        st.pyplot(plt)
+
+        # **Show Data Table**
+        if st.checkbox("Show Data Table"):
+            st.dataframe(data)
 except FileNotFoundError:
-    st.write("No data available yet.")
+    st.write("No data available yet. Submit responses to populate insights.")
+
+# **Download Data Option for Researchers**
+st.subheader("📥 Download Data for Research")
+if os.path.exists("data.csv"):
+    with open("data.csv", "rb") as file:
+        st.download_button(label="Download CSV Data", data=file, file_name="microaggression_data.csv", mime="text/csv")
+
+st.write("🔬 Developed as a research tool for understanding microaggressions in social psychology.")