Research

Beginning to delve into research in the intersection of what fascinates me and what can impact society. Currently exploring Artificial Intelligence, Human-Computer Interaction (HCI), and Web 3.

Research Interests

Reinforcement Learning

Designing interaction-driven algorithms for decisions across robotics, education, healthcare and digital platforms. Building safe and data-efficient agents that balance exploration-exploitation, learn from simulation/offline data with human feedback, and improve under uncertainty.

Human-Computer Interaction

Exploring human-centered design and interactive tech to elevate usability, accessibility, and trust—from immersive interfaces to assistive tools. Creating adaptive, inclusive systems that align with human values and deliver responsible, equitable impact.

Artificial Intelligence

Developing learning algorithms, representations, and generative models that reshape perception, reasoning, and creation across domains. Building trustworthy, human-aligned AI that augments people, automates routine work, accelerates discovery, and scales equitable, sustainable impact.

Web 3

Leveraging decentralized protocols, verifiable data, and smart contracts to reimagine identity, ownership, and coordination. Building open, privacy-preserving, interoperable systems with secure, scalable token governance for equitable global participation.

Publications

Ongoing and completed work.

2023

1 paper

Hate Speech Detection in Algerian Dialect using Deep Learning

NAML, NeurIPS'2320 September 2023complete
Authors: Sin Liang Lee, Lamia Sekkai, Dihia Lanasri, Juan Olano, Sifal Klioui
Published in: North Africans in Machine Learning, NeurIPS 2023
Abstract

With the proliferation of hate speech on social networks under different formats, such as abusive language, cyberbullying, and violence, etc., people have experienced a significant increase in violence, putting them in uncomfortable situations and threats. Plenty of efforts have been dedicated in the last few years to overcome this phenomenon to detect hate speech in different structured languages like English, French, Arabic, and others. However, a reduced number of works deal with Arabic dialects like Tunisian, Egyptian, and Gulf, mainly the Algerian ones. To fill in the gap, we propose in this work a complete approach for detecting hate speech on online Algerian messages. Many deep learning architectures have been evaluated on the corpus we created from some Algerian social networks (Facebook, YouTube, and Twitter). This corpus contains more than 13.5K documents in Algerian dialect written in Arabic, labeled as hateful or non-hateful. Promising results are obtained, which show the efficiency of our approach.

Keywords
Hate SpeechAlgerian DialectDeep Learning DziriBERTFastText
PDFarXiv
Preprint