About

AI Student & NLP Researcher.
I'm currently enjoying exploring the fascinating land of natural language processing as an AI student. I'm interested in seeing the theater of sentiments anytime, anywhere.
- Degree: Master
- Website: rezang.github.io
- Email: rezang52@gmail.com
- City: Bābol, Mazandaran, Iran
- Favorite Book: A Farewell to Arms
- Favorite Hobby: Watching the Sky
- Favorite Movie: Saraband (2003)
- Favorite Flower: Pothos Aureus
I'm an Artificial Intelligence researcher specializing in Natural Language Processing and Machine Learning. With a Master's in AI, I've developed and deployed deep learning models for sentiment analysis, chatbots, and predictive systems, focusing on real-world impact. My expertise spans transformers, neural networks, and data analytics. I've tackled challenges like short/incomplete text sentiment detection and pioneered the first Persian AMR corpus. My work has achieved state-of-the-art results, published in respected journals. Fluent in Python and experienced with leading AI tools, I actively contribute to the field's growth and am passionate about leveraging technology to solve complex problems and transform lives.
Skills
Descriptions for my skills

Programming
Skilled in Python
Familiar with PHP

Deep Learning
Transformers,
RNNs, LSTM,
GRU, CNN,
AutoEncoders

Machine Learning
Clustering, Decision Tree
SVM, MLP, RL,
Ensemble Models,
Logistic Regression

AI Packages
Pytorch, Numpy,
Pandas, Matplotlib,
WandB, PLotly,
Scikit-learn
Resume
Research Experience
AI Researcher
2022 - 2025
K. N. T. University of Technology
Architected a novel deep learning pipeline for sentiment polarity detection in short, noisy texts. The system uses a three-phase methodology: an automatic correction pipeline, a RoBERTa-based denoising autoencoder, and a feature-fusion classifier. It achieved state-of-the-art F1-scores, outperforming baselines by 10% on the Sentiment 140 dataset.
AI Researcher
2021 - 2023
K. N. T. University of Technology
Developed a system to fix biased hotel recommendations from imbalanced, multilingual reviews. It uses a T5 transformer for data augmentation and an enhanced XLM-ROBERTa classifier. The model achieved an 89% Macro F1-score, outperforming the baseline by 5% and reducing inference time by over 60%. Published in CyS Journal.
AI Researcher
2021 - 2023
K. N. T. University of Technology
To address the lack of Persian semantic resources, I co-developed the first Persian Abstract Meaning Representation (PAMR) corpus by annotating 1,020 sentences. I then pioneered a data augmentation method using this corpus, which boosted a sentiment analysis model's F1-score and accuracy by 12%. The research was published in an ACM journal.
Education
M.Sc. Student of Artificial Intelligence
at K. N. Toosi University of Technology
2020 - 2023
Tehran, Iran
- Notable Courses: Natural Language Processing, Neural Networks, Recommender Systems, Information Retrieval, Evolutionary Computation
- Thesis: Sentiment Analysis of Short and Incomplete Text using Transformers and Attention Mechanism; under supervision of Dr. Chitra Dadkhah
- Thesis Grade: (20/20 -- 4/4)
- GPA: (18.32/20 -- 3.88/4)
Bachelor of Computer Engineering
at Shomal University
2017 - 2020
Amol, Mazandaran, Iran
- Notable Courses: Machine Learning, Artificial Intelligence, Algorithm Design, Data Structures, Formal Languages and Automata Theory, Engineering Probability and Statistics
- Thesis: A machine learning-based model for spam detection on mobile phone short message service (SMS); under supervision of Dr. Hamidreza Koohi
- Thesis Grade: (20/20 -- 4/4)
- GPA: (17.61/20 -- 3.44/4)
Research Interests
Deep Learning
A class of ML algorithms that employs neural networks to extract higher-level characteristics from input.
Natural Language Processing
The ability of a computer program to understand human language as it is spoken and written
Recommender System
To generate meaningful recommendations to a collection of users for items or products that might interest them
Certificates
Click this button to see the certificate.
- All
- Deep Learning
- Natural Language Processing
- Learning English
- Programming