Upload README.md

README.md

@@ -1,5 +1,5 @@
 ---
-title: FIDIC Hierarchical Responsibility Classifier
+title: Automatic Assignment of Project Responsibilities
 emoji: 🏗️
 colorFrom: blue
 colorTo: green
@@ -10,9 +10,9 @@ pinned: false
 license: mit
 ---
 
-# FIDIC Contract Hierarchical Responsibility Classifier
+# Automatic Assignment of Project Responsibilities to Stakeholders
 
-This application performs **hierarchical classification** of construction contract clauses from FIDIC Red Book contracts. It uses an ensemble of machine learning models to:
+This application performs **hierarchical classification** of construction responsibility descriptions. It uses an ensemble of machine learning models to:
 
 1. **Level 1 - Party Classification:** Identifies the main responsible party (e.g., Employer, Contractor, Engineer)
 2. **Level 2 - Stakeholder Classification:** Determines the specific stakeholder role within that party
@@ -59,14 +59,14 @@ texts,category
 This application is based on research from:
 - **Institution:** Department of Civil Engineering, Karadeniz Technical University, Trabzon, Turkey
 - **Authors:** Hayri Burak Altuntaş, Hasan Basri Başağa
-- **Topic:** Hierarchical Classification of Responsibility Allocation in FIDIC Red Book Contracts
+- **Topic:** Automatic assignment of project responsibilities to stakeholders in BIM information management
 
 ## Technical Details
 
 - **NLP Pipeline:** Text cleaning, stopword removal, lemmatization
 - **Feature Engineering:** Count vectorization and categorical encoding
 - **Models:** 7 different ML algorithms in soft voting ensemble
-- **Optimization:** Trained on FIDIC Red Book contract dataset
+- **Optimization:** Trained on a domain-specific construction responsibility dataset
 
 The upload limit is 50 MB and 100,000 rows to keep memory usage predictable in a
 Streamlit deployment. Text and category must be selected from different columns.