Home Original page

DominiqueLoyer - Overview

πŸ‘¨β€πŸ”¬ Dominique S. Loyer

ORCID Google Scholar ResearchGate Website sysCRED Plateforme ISC

PhD Candidate in Cognitive Informatics at UniversitΓ© du QuΓ©bec Γ  MontrΓ©al (UQAM)

Research Interests:

  • πŸ€– Algorithmic Bureaucracy & Governance
  • πŸ” Explainable AI (xAI) & Transparency
  • πŸ“Š Recommendation Systems & Collaborative Filtering
  • 🌐 Digital Sociology & Information Credibility
  • βš–οΈ AI Ethics & Accountability

πŸ’– Support My GITHUB Open Projects

GitHub Sponsors Buy Me A Coffee

SysCRED — Système Neuro-Symbolique de Vérification de Crédibilité

sysCRED Version PyPI version DOI Python License: MIT Open In Colab OWL RDF Ontologie Neuro--Symbolic HTML Jupyter Node.js Flask Docker Render Supabase License

PhD Thesis Prototype β€” Dominique S. Loyer (UQAM)
Citation Key: loyerModelingHybridSystem2025

[!NOTE] **Version stable : v2.4.1 (12 mars 2026) β€” (dashboard explainers, TREC metrics, GraphRAG)**
>  - **Fact-Checking** multi-sources (Google Fact Check API)
>  - **E-E-A-T** (Experience, Expertise, Authority, Trust)
>  - **NER** β€” Extraction d'entitΓ©s nommΓ©es (spaCy)
>  - **GraphRAG** β€” RΓ©seau Neuro-Symbolique (D3.js)
>  - **MΓ©triques** β€” Precision, Recall, nDCG, MRR
>  - **Bias Analysis** β€” DΓ©tection de biais

Site institutionnel: https://syscred.uqam.ca

πŸ” systemFactChecking – Hybrid Information Credibility Verification System

A hybrid fact-checking system combining predicate-logic rules, ontologies (OWL), and neuro-symbolic AI to evaluate the credibility of information sources.

SysCRED est un système hybride de fact-checking combinant :

  • Symbolic AI : Raisonnement par rΓ¨gles et ontologies (OWL/RDF)

  • Neural AI : Transformers pour NER, sentiment, cohΓ©rence

  • IR Engine : Recherche d’évidence (BM25, TF-IDF, TREC)

  • GraphRAG : MΓ©moire contextuelle par graphe de connaissances

  • E-E-A-T : Scoring qualitΓ© Google (Experience, Expertise, Authority, Trust)

  • Technologies: Python, NLP, OWL Ontologies, Machine Learning, Neuro-symbolic AI

  • Status: Active Research (Doctoral Project) sysCRED

  • πŸ“‚ Repository

  • πŸ“„ Modeling Paper ISBN

  • πŸ“„ Ontology Paper ISBN

  • πŸ“„ Beamer Presentation - (PDF)

sysCRED PyPI version DOI Python 3.8+ License: MIT Open In Colab Kaggle OWL RDF License: MIT

refactorisation de sysCRED (14 mars 2026)

systemFactChecking_Production/
β”œβ”€β”€ src/
β”‚   └── syscred/                    ← Package Python principal
β”‚       β”œβ”€β”€ __init__.py
β”‚       β”œβ”€β”€ core/                   ← CΕ“ur du systΓ¨me
β”‚       β”‚   β”œβ”€β”€ config.py           ← Configuration centralisΓ©e
β”‚       β”‚   β”œβ”€β”€ verification_system.py
β”‚       β”‚   └── scoring.py
β”‚       β”œβ”€β”€ api/                    ← Interface web
β”‚       β”‚   β”œβ”€β”€ backend_app.py      ← Flask app
β”‚       β”‚   β”œβ”€β”€ routes/
β”‚       β”‚   └── middleware/
β”‚       β”œβ”€β”€ ml/                     ← ModΓ¨les ML
β”‚       β”‚   β”œβ”€β”€ sentiment.py
β”‚       β”‚   β”œβ”€β”€ ner_analyzer.py     ← Γ€ fusionner depuis HF
β”‚       β”‚   └── eeat_calculator.py  ← Γ€ fusionner depuis HF
β”‚       β”œβ”€β”€ graph/                  ← GraphRAG & Ontologie
β”‚       β”‚   β”œβ”€β”€ graph_rag.py
β”‚       β”‚   β”œβ”€β”€ ontology_manager.py
β”‚       β”‚   └── queries.py
β”‚       β”œβ”€β”€ ir/                     ← TREC & Information Retrieval
β”‚       β”‚   β”œβ”€β”€ ir_engine.py
β”‚       β”‚   β”œβ”€β”€ trec_retriever.py
β”‚       β”‚   └── eval_metrics.py
β”‚       β”œβ”€β”€ datasets/               ← Gestion datasets
β”‚       β”‚   └── liar_dataset.py
β”‚       └── utils/                  ← Utilitaires
β”‚           β”œβ”€β”€ api_clients.py
β”‚           β”œβ”€β”€ database.py
β”‚           └── helpers.py
β”‚
β”œβ”€β”€ data/                           ← DonnΓ©es (hors git pour gros fichiers)
β”‚   β”œβ”€β”€ ontology/
β”‚   β”‚   β”œβ”€β”€ sysCRED_onto26avrtil.ttl
β”‚   β”‚   └── sysCRED_data.ttl
β”‚   └── datasets/
β”‚       β”œβ”€β”€ liar/                   ← Dataset LIAR
β”‚       └── trec/                   ← Corpus TREC AP88-90 (276MB)
β”‚
β”œβ”€β”€ docs/                           ← Documentation
β”‚   β”œβ”€β”€ DEV_LOGS/                   ← Journaux de dΓ©veloppement
β”‚   β”œβ”€β”€ PUBLICATIONS/               ← Papers et prΓ©sentations
β”‚   └── API.md
β”‚
β”œβ”€β”€ tests/                          ← Tests
β”‚   β”œβ”€β”€ unit/
β”‚   β”œβ”€β”€ integration/
β”‚   └── benchmarks/
β”‚
β”œβ”€β”€ notebooks/                      ← Jupyter notebooks
β”‚   └── exploration/
β”‚
β”œβ”€β”€ deploy/                         ← Configurations dΓ©ploiement
β”‚   β”œβ”€β”€ huggingface/                ← SpΓ©cifique HF Space
β”‚   β”‚   β”œβ”€β”€ Dockerfile.hf
β”‚   β”‚   β”œβ”€β”€ requirements-hf.txt
β”‚   β”‚   └── static/                 ← Assets HF
β”‚   └── docker/                     ← Docker gΓ©nΓ©rique
β”‚       β”œβ”€β”€ Dockerfile
β”‚       └── docker-compose.yml
β”‚
β”œβ”€β”€ scripts/                        ← Scripts utilitaires
β”‚   β”œβ”€β”€ start_syscred.sh
β”‚   β”œβ”€β”€ deploy_huggingface.sh
β”‚   └── run_benchmarks.py
β”‚
β”œβ”€β”€ 99_Archive/                     ← ARCHIVES (jamais supprimΓ©es)
β”‚   └── 2026-03-14_restructuration/
β”‚       β”œβ”€β”€ systemFactChecking-1/   ← Copie complΓ¨te prΓ©servΓ©e
β”‚       β”œβ”€β”€ syscred-space_backup/   ← Version HF prΓ©servΓ©e
β”‚       β”œβ”€β”€ v2_syscred/             ← Ancienne version
β”‚       β”œβ”€β”€ syscred_legacy/
β”‚       └── SysCRED_v2.1_Update/
β”‚       └── README.md               ← Documentation des archives
β”‚
β”œβ”€β”€ pyproject.toml                  ← Configuration package Python
β”œβ”€β”€ requirements.txt
β”œβ”€β”€ requirements-dev.txt
β”œβ”€β”€ .env.example
β”œβ”€β”€ .gitignore                      ← Mis Γ  jour avec data/large
└── README.md                       ← Mis Γ  jour

πŸ“š Featured Publications

πŸ† PhD (Examen de synthΓ¨se doctoral)

Le LΓ©viathan Algorithmique : pouvoir, opacitΓ© et responsabilitΓ© Γ  l'Γ¨re de l'intelligence artificielle
ISBN DOI

πŸ“ Selected Papers

  • Modeling a Hybrid System for Verifying Information Credibility (2025) ISBN DOI

  • Hybrid System Ontology for Information Source Verification (2025)
    ISBN DOI

πŸ“š TREC Evaluation System

Evaluation of Information Retrieval Models on TREC AP 88-90 (2025)
ISBN Paper DOI

Évaluation comparative de modèles de recherche d'information sur les collections TREC AP 88-90.

Technologies : Python β€’ Information Retrieval β€’ BM25 β€’ TF-IDF β€’ Vector Space Models

RΓ©sultats :

  • πŸ“Š Analyse de ~243,000 documents
  • πŸ“ˆ Comparaison BM25 vs. VSM
  • 🎯 MΓ©triques MAP, NDCG, Precision@K

πŸ“„ Lire l'article

πŸ“„ View all publications β†’

πŸ’» Research Projects

πŸ” Information Credibility Verification System

A hybrid system combining predicate logic and ML/AI for assessing information source credibility.

  • Technologies: Python, NLP, Ontologies (OWL), Machine Learning
  • Status: Active Research
  • πŸ“‚ Repository | πŸ“„ Paper

🌐 Web Science Ontology

OWL ontology for modeling information verification systems.

  • Technologies: OWL, RDF, ProtΓ©gΓ©
  • Status: Published
  • πŸ“‚ Repository | πŸ“„ Paper

πŸ”€ Neural Machine Translation (English-Russian)

Neural machine translation system with attention mechanisms.

  • Technologies: Python, TensorFlow, PyTorch, NMT
  • Status: Completed
  • πŸ“‚ Repository | πŸ“„ Paper ISBN

πŸ› οΈ Technical Skills

Programming Languages:
Python R LaTeX Bash

AI/ML Frameworks:
TensorFlow PyTorch scikit-learn

Research & Productivity Tools:
Zotero Obsidian Notion Git

πŸ“Š GitHub Statistics

🎯 Current Focus

  • πŸ”¬ Completing PhD dissertation on algorithmic bureaucracy
  • πŸ“ Publishing research on AI transparency and accountability
  • πŸ’‘ Developing explainable AI frameworks for recommendation systems
  • 🌍 Contributing to open science and reproducible research

πŸ“š Publications Highlights

AnnΓ©e Titre Type DOI
2025 Le Léviathan Algorithmique : pouvoir, opacité et responsabilité à l'ère de l'intelligence artificielle Examen de synthèse doctoral DOI
2025 Modeling a Hybrid System for Verifying the Credibility of Information Sources Preprint DOI
2025 Hybrid System for Verifying Credibility: An Ontology Preprint DOI
2025 Evaluation of Information Retrieval Models on TREC AP 88-90 Preprint DOI
2025 Development and Evaluation of an English-to-Russian Neural MT System Preprint DOI

View All Publications

πŸ“« Contact & Links

πŸ“œ License

Unless otherwise specified, research code is released under MIT License.
Academic publications follow their respective copyright agreements.

⭐ If you find my work interesting, consider following or starring relevant repositories!

Profile views