Civil Engineer & AI Enthusiast

Ziad
Abdullah
Alotaibi
زياد
عبدالله
العتيبي

I build أبني

Civil Engineering AI & Machine Learning Arabic NLP Web Development Automation
View My Work ↓ Get in Touch
6+ Projects
6 Papers
41+ Technologies
Scroll to explore
PHP MySQL ZATCA API AI/ML Bootstrap Arabic RTL UI PDF Generation Chart.js PDF Reports Python Tkinter/PyQt SQLite Excel Export PyTorch Telegram Bot API Computer Vision Hugging Face Transformers NLLB-200 Gradio Arabic NLP BERT Adversarial ML Pandas Hugging Face Geometric NLP Arabic LLMs Llama-3 Qwen-2.5 CAMeLBERT NLP Benchmarking BIM AI Construction Management Civil Engineering Digital Transformation Governance Non-Profit Organizations AI Governance Differential Privacy Text Classification Ethics PHP MySQL ZATCA API AI/ML Bootstrap Arabic RTL UI PDF Generation Chart.js PDF Reports Python Tkinter/PyQt SQLite Excel Export PyTorch Telegram Bot API Computer Vision Hugging Face Transformers NLLB-200 Gradio Arabic NLP BERT Adversarial ML Pandas Hugging Face Geometric NLP Arabic LLMs Llama-3 Qwen-2.5 CAMeLBERT NLP Benchmarking BIM AI Construction Management Civil Engineering Digital Transformation Governance Non-Profit Organizations AI Governance Differential Privacy Text Classification Ethics
Selected Works

Projects & Products

From SaaS platforms to intelligent bots — here's what I've built.

SACopilot: AI Smart Logistics Assistant
01 Web App

SACopilot: AI Smart Logistics Assistant

An AI-powered logistics management platform for Saudi businesses. Features smart shipment search, real-time risk analysis, ZATCA-compliant e-invoicing, and a full auditor portal.

PHP MySQL ZATCA API
Ejar: Digital Property Management Platform
02 Web App

Ejar: Digital Property Management Platform

A full-stack Arabic-first property management system for Saudi landlords. Manage units, tenants, contracts, maintenance, utility bills, and generate financial reports — all in one place.

PHP MySQL Arabic RTL UI
Saudi Local Content Ledger
03 Web App

Saudi Local Content Ledger

A compliance platform for tracking and reporting Saudi local content (LC) percentages across procurement and projects — aligned with Vision 2030 requirements.

PHP MySQL Chart.js
Smart Logistics System
04 Desktop Software

Smart Logistics System

A desktop-based intelligent logistics management system with a full GUI. Handles shipments, inventory, suppliers, and generates reports — built for operations teams without internet dependency.

Python Tkinter/PyQt SQLite
🤖
05 Telegram Bot

Saudi Plant Disease Doctor

An AI Telegram bot that diagnoses plant diseases from a single photo. Powered by 18 specialized AI models trained on Saudi agriculture crops — available 24/7 and fully in Arabic.

Python PyTorch Telegram Bot API
🧠
06 AI / NLP Model

Saudi Dialect AI Translator

A fine-tuned AI model that translates English text into four authentic Saudi Arabic dialects: Najdi, Hijazi, Eastern, and Southern. Trained on 31,000+ sentence pairs with a BLEU score of 30.04.

Python Hugging Face Transformers NLLB-200
Swipe to see more
Academic Research

Research Papers

Published and ongoing research in Arabic NLP and language models.

🔬 R01 Under Review

The Diacritic Blindspot: Robustness in Arabic BERT Models

A comprehensive adversarial robustness benchmark of Arabic BERT models against five attack types. Reveals a critical accuracy–robustness trade-off: MARBERT resists diacritical attacks (>92% retention) but sacrifices baseline accuracy. The mechanism is traced to tokenizer construction.

Read paper →
📐 R02 Under Review

The Geometry Gap: Semantic Anisotropy in Arabic LLMs

Challenges the assumption that newer, larger LLMs are universally superior. Demonstrates that modern generative LLMs (Qwen 2.5, Llama 3.1) suffer from severe semantic anisotropy in Arabic — while the 110M-parameter AraBERT outperforms 8B+ LLMs for semantic retrieval tasks.

Read paper →
🏆 R03 Under Review

Less is More: Benchmarking LLMs for Arabic Sentiment Analysis

A benchmark study comparing generalist LLMs (Llama-3, Qwen-2.5) against specialized encoder models (CAMeLBERT) on noisy Arabic sentiment analysis. Qwen-2.5 achieves 91.5% accuracy — but with 28% higher latency than Llama-3.

Read paper →
🏗️ R04 ✓ Published

Activating BIM Using AI: An Applied Analytical Study

A published study on activating Building Information Modeling (BIM) in construction project management using artificial intelligence tools.

Read paper →
🏛️ R05 ✓ Published

Governance Excellence in Non-Profits via Digital Transformation

A published study on how digital and strategic transformation drives governance excellence in non-profit organizations.

Read paper →
🔐 R06 ✓ Published

AI Governance through Ethical Data Handling and Differential Privacy

A published study on strengthening AI governance through ethical handling of sensitive data, with applications in text classification and differential privacy.

Read paper →

Let's work
together
لنعمل
معاً

Have a project in mind, or need access to project files? Feel free to reach out.

✉️
Personal Email
ziad.ab90@gmail.com
📞
Phone / WhatsApp
0560464645