Update app.py

app.py

@@ -1,5 +1,4 @@
 import streamlit as st
-st.write("Test system if working")
 import zipfile
 import os
 import requests
@@ -16,8 +15,7 @@ headers = {
     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
 }
 
-# Debugging: Print current working directory initially
-st.write(f"Initial Current Working Directory: {os.getcwd()}")
+
 
 # Check if the model folder exists
 zip_file_path = "my_authorship_model_zip.zip"
@@ -60,17 +58,8 @@ if not os.path.exists('my_authorship_model'):
         st.write(f"Failed to download or extract the model: {e}")
         exit(1)
 else:
-    st.write("Model folder exists")
-
-# Debugging: Print current working directory after extraction
-st.write(f"Current Working Directory After Extraction: {os.getcwd()}")
+    st.write("System Ready !!")
 
-# Debugging: Check if model folder contains required files
-try:
-    model_files = os.listdir('my_authorship_model')
-    st.write(f"Files in model folder: {model_files}")
-except Exception as e:
-    st.write(f"Could not list files in model folder: {e}")
 
 # Download the required files
 file_urls = {
@@ -115,11 +104,10 @@ def predict_author(new_text, model, tokenizer, label_encoder):
 
     return predicted_label, author_probabilities
 
-st.markdown("CNN : version: 1.2")
 new_text = st.text_area("Input your text here")
 
 # Creates a button named 'Press me'
-press_me_button = st.button("Which Model Used?")
+press_me_button = st.button("Writer or Robot?")
 
 if press_me_button:
     predicted_author, author_probabilities = predict_author(new_text, loaded_model, tokenizer, label_encoder)
@@ -129,3 +117,58 @@ if press_me_button:
     st.write("Probabilities for each author are (sorted):")
     for author, prob in sorted_probabilities:
         st.write(f"{author}: {prob * 100:.2f}%")
+
+import streamlit as st
+
+st.title("Smart Authorship Detection System of AI-Generated Text Models")
+
+# Slogan under the title
+st.subheader("Uncover the Invisible Ink: Who's the Author?")
+
+# Using expander to make FAQ sections
+st.subheader("Frequently Asked Questions (FAQ)")
+
+# Small Description
+with st.expander("What is this project about?"):
+    st.write("""
+    This project is part of an MSc in Data Analytics at the University of Portsmouth.
+    Developed by Jaifar Al Shizawi, it aims to identify whether a text is written by a human or a specific Large Language Model (LLM) like ChatGPT-3, ChatGPT-4, Google Bard, or HuggingChat.
+    For inquiries, contact [[email protected]](mailto:[email protected]).
+    Supervised by Dr. Mohamed Bader.
+    """)
+
+# System Details
+with st.expander("How does the system work?"):
+    st.write("""
+    The system is trained using a CNN model on a dataset of 140,546 paragraphs, varying in length from 10 to 500 words.
+    It achieves an accuracy of 0.9964 with a validation loss of 0.094.
+    """)
+
+# Data Storage Information
+with st.expander("Does the system store my data?"):
+    st.write("No, the system does not collect or store any user input data.")
+
+# Use-case Limitation
+with st.expander("Can I use this as evidence?"):
+    st.write("""
+    No, this system is a Proof of Concept (POC) and should not be used as evidence against students or similar entities.
+    """)
+
+# Background and Context
+with st.expander("Background and Context"):
+    st.write("""
+    The proliferation of AI and Large Language Models (LLMs) like ChatGPT and Google Bard has raised questions about authorship. This project aims to analyze and predict the unique features of these models compared to human-written text.
+    """)
+
+# Problem Statement
+with st.expander("Problem Statement"):
+    st.write("""
+    Most AI authorship detection systems fail to identify the specific LLM behind a text. This research aims to fill this gap, offering detailed analysis on various LLMs and human writing.
+    """)
+
+# Aim and Objectives
+with st.expander("Aim and Objectives"):
+    st.write("""
+    The project aims to help staff at the University of Portsmouth distinguish between student-written artifacts and those generated by LLMs. It focuses on text feature extraction, model testing, and implementing a user-friendly dashboard among other objectives.
+    """)
+