.

.gitignore

@@ -0,0 +1,129 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

.streamlit/config.toml

@@ -0,0 +1,8 @@
+[server]
+port = 8501
+
+[browser]
+gatherUsageStats = false
+
+[theme]
+base="light"

README.md

@@ -0,0 +1,2 @@
+# Intention Study
+

app.py

@@ -0,0 +1,149 @@
+import streamlit as st
+import pandas as pd
+import json
+import scrubadub
+from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
+from pymongo.mongo_client import MongoClient
+from pymongo.server_api import ServerApi
+from datetime import datetime
+from uuid import uuid4
+
+# -----------------------------
+# Consent Setup
+# -----------------------------
+st.set_page_config(page_title="ChatGPT Log Analyzer", page_icon="🤖")
+
+if "consent" not in st.session_state:
+    st.session_state.consent = ""
+
+placeholder = st.empty()
+with placeholder.container():
+    with st.expander("Consent", expanded=True):
+        st.markdown("##### Take Part in Our Study")
+        st.markdown("""
+        Please consider participating in our research study on ChatGPT interactions.  
+        In this study, you will be asked to upload ChatGPT logs. These will be analyzed for sentiment, redacted to remove personal information, and stored in a research database.  
+
+        **You must be 18 years or older to participate.**  
+        You can still use the app without sharing your data by clicking **'No, I do not consent'**.
+        """)
+
+        st.radio(
+            "**Do you consent to participating in this study and sharing anonymized information?**", 
+            ["", "Yes, I consent", "No, I do not consent"], 
+            key="consent", horizontal=True
+        )
+
+if st.session_state.consent == "Yes, I consent":
+    placeholder.empty()
+    if "id" not in st.session_state:
+        st.session_state.id = datetime.now().strftime('%Y%m-%d%H-%M-') + str(uuid4())
+    st.success("✅ You consented to participate.")
+    st.info(f"Your anonymized ID is: **{st.session_state.id}**. Keep this if you want your data deleted later.")
+
+elif st.session_state.consent == "No, I do not consent":
+    placeholder.empty()
+    st.warning("⚠️ You did not consent. You can still use the app, but your logs will not be stored.")
+
+# -----------------------------
+# Parser Function
+# -----------------------------
+def parse_chatgpt_export(data):
+    rows = []
+    conversations = data.get("conversations", [])
+    for conv in conversations:
+        conv_id = conv.get("id")
+        title = conv.get("title")
+        mapping = conv.get("mapping", {})
+
+        for msg_id, msg in mapping.items():
+            author = msg.get("author", {})
+            role = author.get("role", "unknown")
+            content = msg.get("content", {})
+            parts = content.get("parts", [])
+            text = "\n".join(parts) if parts else ""
+
+            rows.append({
+                "conversation_id": conv_id,
+                "title": title,
+                "message_id": msg_id,
+                "role": role,
+                "content": text,
+                "create_time": msg.get("create_time")
+            })
+    return pd.DataFrame(rows)
+
+# -----------------------------
+# File Upload
+# -----------------------------
+uploaded_file = st.file_uploader("Upload ChatGPT export (.json)", type=["json"])
+
+if uploaded_file:
+    data = json.load(uploaded_file)
+    if isinstance(data, dict) and "conversations" in data:
+        df = parse_chatgpt_export(data)
+        convo_titles = df["title"].unique()
+    else:
+        st.error("Unsupported JSON structure")
+        st.stop()
+
+    # -----------------------------
+    # Session State for Pagination
+    # -----------------------------
+    if "convo_index" not in st.session_state:
+        st.session_state.convo_index = 0
+
+    # -----------------------------
+    # Dropdown Selection
+    # -----------------------------
+    selected_title = st.selectbox("Select Conversation", options=convo_titles, index=st.session_state.convo_index)
+    st.session_state.convo_index = list(convo_titles).index(selected_title)
+
+    # -----------------------------
+    # Pagination Buttons
+    # -----------------------------
+    col1, col2, col3 = st.columns([1,2,1])
+    with col1:
+        if st.button("⬅ Previous") and st.session_state.convo_index > 0:
+            st.session_state.convo_index -= 1
+            selected_title = convo_titles[st.session_state.convo_index]
+    with col3:
+        if st.button("Next ➡") and st.session_state.convo_index < len(convo_titles)-1:
+            st.session_state.convo_index += 1
+            selected_title = convo_titles[st.session_state.convo_index]
+
+    # -----------------------------
+    # Filter Selected Conversation
+    # -----------------------------
+    convo_df = df[df["title"] == selected_title].copy()
+
+    # -----------------------------
+    # Scrub + Sentiment
+    # -----------------------------
+    cleaner = scrubadub.Scrubber()
+    convo_df["redacted"] = convo_df["content"].apply(lambda x: cleaner.clean(str(x)))
+
+    analyzer = SentimentIntensityAnalyzer()
+    convo_df["sentiment"] = convo_df["content"].apply(lambda x: analyzer.polarity_scores(str(x))["compound"])
+
+    # -----------------------------
+    # Show Conversation
+    # -----------------------------
+    st.subheader(f"💬 Conversation ({st.session_state.convo_index+1}/{len(convo_titles)}): {selected_title}")
+    st.dataframe(convo_df[["role", "redacted", "sentiment", "create_time"]])
+
+    # -----------------------------
+    # Optional: Save to MongoDB
+    # -----------------------------
+    if st.button("📥 Save Conversation to Database"):
+        with MongoClient(st.secrets["mongo"], server_api=ServerApi('1')) as client:
+            db = client.bridge
+            collection = db.app
+            record = {
+                "conversation_id": convo_df["conversation_id"].iloc[0],
+                "title": selected_title,
+                "inserted_at": datetime.utcnow(),
+                "messages": convo_df.to_dict(orient="records")
+            }
+            collection.insert_one(record)
+            st.success(f"✅ Conversation '{selected_title}' saved to MongoDB.")

requirements.txt

@@ -0,0 +1,8 @@
+streamlit==1.23.0
+pymongo[srv]==3.12
+datetime
+uuid
+numpy
+scrubadub
+textblob
+pandas

sample_chat.json

@@ -0,0 +1,62 @@
+{
+  "conversations": [
+    {
+      "id": "conv_123456",
+      "title": "Trip Planning",
+      "create_time": "2023-08-01T12:34:56.000Z",
+      "mapping": {
+        "msg_1": {
+          "id": "msg_1",
+          "author": { "role": "user" },
+          "create_time": "2023-08-01T12:34:56.000Z",
+          "content": {
+            "content_type": "text",
+            "parts": [
+              "Hi, my name is John Doe and my email is john.doe@example.com. Can you help me plan a trip?"
+            ]
+          }
+        },
+        "msg_2": {
+          "id": "msg_2",
+          "author": { "role": "assistant" },
+          "create_time": "2023-08-01T12:35:10.000Z",
+          "content": {
+            "content_type": "text",
+            "parts": [
+              "Of course! Where would you like to travel?"
+            ]
+          }
+        }
+      }
+    },
+    {
+      "id": "conv_654321",
+      "title": "Job Advice",
+      "create_time": "2023-09-01T15:00:00.000Z",
+      "mapping": {
+        "msg_1": {
+          "id": "msg_1",
+          "author": { "role": "user" },
+          "create_time": "2023-09-01T15:00:01.000Z",
+          "content": {
+            "content_type": "text",
+            "parts": [
+              "Hi, I’m Jane Smith. I’m applying for jobs and my phone is (555) 222-9999. Can you review my resume?"
+            ]
+          }
+        },
+        "msg_2": {
+          "id": "msg_2",
+          "author": { "role": "assistant" },
+          "create_time": "2023-09-01T15:00:20.000Z",
+          "content": {
+            "content_type": "text",
+            "parts": [
+              "Sure! Please paste your resume text here and I’ll give feedback."
+            ]
+          }
+        }
+      }
+    }
+  ]
+}