Mr.Ā Nisar Hussain Instituto Politechnico Nacional, Mexico City, Mexico
Nisar Hussain is a researcher affiliated with the Instituto PolitĆ©cnico Nacional (IPN) in Mexico City, Mexico. He is currently enrolled in the Doctorate in Computer Science program at IPN’s Centro de InvestigaciĆ³n en ComputaciĆ³n (CIC), focusing his research on offensive language detection and sentiment analysis in code-mixed text on social media.Throughout his academic career, Hussain has contributed to various studies in the field of Natural Language Processing (NLP). Notably, he co-authored the paper titled “ORUD-Detect: A Comprehensive Approach to Offensive Language Detection in Roman Urdu Using Hybrid Machine LearningāDeep Learning Models with Embedding Techniques,” published in the journal Information in February 2025.In addition to his work on offensive language detection, Hussain has explored other areas of NLP. He co-authored a study on guilt detection in text, which was published in Scientific Reports in July 2023.
Google scholar
orcid
Education :
Ph.D. in Computer Science (2022-2025, Ongoing)
Instituto PolitĆ©cnico Nacional, MĆ©xicoMaster’s in Computer Science (2014-2017)
University of Agriculture, Faisalabad, PakistanBachelor of Science in Computer Science (BSCS) (2010-2014)
COMSATS University Islamabad, Sahiwal Campus
Experience :
With 4+ years of experience in developing and deploying ML and NLP systems, I have actively contributed to multiple projects, applying NLP techniques for real-world problem-solving. I have worked with large, complex datasets, implementing hybrid ML-DL approaches for automated text processing, sentiment analysis, and multilingual content understanding. My research collaborations span multiple institutions, focusing on AI-driven solutions for text analysis and detection tasks.
Research Focus :
I specialize in Natural Language Processing (NLP) and Machine Learning, with a particular emphasis on Offensive Language Detection and Sentiment Analysis of Code-Mixed Data. My research explores multilingual and low-resource language models, leveraging and fine-tuning mBERT, XLM-R, IndicBERT, and Google’s BERT-based models. I am particularly interested in hate speech detection, sentiment analysis, language identification, and emotion analysis in complex linguistic environments. My work integrates deep learning techniques, transformers, and hybrid ML-DL models to improve text processing and understanding in diverse multilingual contexts.
Awards:
Published multiple high-impact research papers in leading AI and NLP conferences/journalsActive participant in international AI competitions and workshopsRecognized for contributions to multilingual and low-resource NLP advancements
Publication :
Given their strong publication record, hands-on experience with AI models, and focus on low-resource NLP, the candidate is highly competitive for the Best Researcher Award. Strengthening industry collaborations, increasing research impact, and securing grants will further enhance their research profile.