The DS4EIW 2026 workshop will take place in person on May 4, 2026 in Montréal, Canada, co-located with IEEE ICDE 2026.

Program - May 4, 2026

8:00
9:00
Registration
9:00
10:30
Session 1 - Opening & Keynote
9:00 - 9:10
Opening Remarks & Welcome
9:10 - 9:55
Keynote Talk
Belkacem Chikhaoui, TELUQ University – Beyond Accuracy: Causal and Multimodal AI for Equitable and Inclusive Healthcare (more info)
9:55 - 10:15
Efficient Quantification of Responsibility for the Spread of Misinformation and Disinformation Using the Banzhaf Index
Masatoshi Yoshikawa, Hayate Asazawa
10:15 - 10:30
Discussion
10:30
11:00
Coffee Break
11:00
12:30
Session 2 - AI Safety, Fairness & Trustworthiness
11:00 - 11:20
RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents
Yonas Atinafu, Robin Cohen
11:20 - 11:40
Improving LLM Performance through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI
Yonas Atinafu, Henry Lin, Robin Cohen
11:40 - 12:00
Trusting the Detector: Comparing Explanations for Deepfake Identification Across Modalities
Lucas Kopp, Alina Lytovchenko, Robin Cohen
12:00 - 12:20
Structure Selection for Fairness-Constrained Differentially Private Data Synthesis
Naeim Ghahramanpour, Mostafa Milani
12:20 - 12:30
Discussion
12:30
14:00
Lunch Break
14:00
16:00
Session 3 - Data Science for Society
14:00 - 14:20
From Water Networks to Wellness: Data Science-Driven Design of Human-Inhabited Spaces
Genoveva Vargas-Solar, Peace Ebika, José-Luis Zechinelli-Martini, Celeste Gabriela Cedillo González, Javier-Alfonso Espinosa-Oviedo
14:20 - 14:40
The Human Factor in Data Cleaning: Exploring Preferences and Biases
Hazim AbdElazim, M M Shadman Islam, Mostafa Milani
14:40 - 15:00
Artificial Intelligence and Women’s Work: A Review of Evidence
Francesca Zafonte, Tania Cerquitelli
15:00 - 15:20
Improving Sentiment Analysis of Mobile App Reviews through Emoji and Slang Normalization
Tinne Dey, Zheying Zhang, Kostas Stefanidis
15:20 - 15:40
Uncertainty Aware Adaptive Proximal Policy Optimization for Pixel Based Autonomous Car Racing
Dipanjan Sen
15:40 - 16:00
Closing Remarks by the Workshop Organizers
16:00
16:30
Coffee Break
16:30
Main Conference Events Resume
Belkacem Chikhaoui

Belkacem Chikhaoui
Professor of Data Science, Canada Research Chair in Multimodal Data Mining, TELUQ University

Beyond Accuracy: Causal and Multimodal AI for Equitable and Inclusive Healthcare

AI has improved predictive performance in healthcare, yet often fails to ensure equity and inclusion due to biased data and correlation-driven models. In this talk, Belkacem Chikhaoui argues for a shift toward causal and multimodal AI, integrating diverse data sources (clinical, imaging, physiological, and social) to better capture the complexity of human health. By combining multimodal learning with causal inference, we can reduce bias, improve generalization, and enable more fair and interpretable decision-making. Through real-world case studies in diagnosis and patient monitoring, this talk illustrates how these approaches support more inclusive healthcare systems and outlines key challenges toward building AI that advances both performance and well-being.

About the Speaker

Belkacem Chikhaoui is a professor of data science and holds the Canada Research Chair in Multimodal Data Mining. He earned a PhD in Computer Science from the Université de Sherbrooke. He has been a member of the DOMUS Laboratory (Home Automation and Mobile Computing) and the ProspectUS Laboratory (Data Prospecting) at the Université de Sherbrooke. He also joined the Intelligent Assistive Technology and Systems Lab (IATSL) at the University of Toronto as a postdoctoral researcher.

Before joining TELUQ University, Belkacem Chikhaoui worked as a data science researcher at the Montreal Computer Research Center (CRIM). He is currently a full professor in the Department of Science and Technology and a researcher at the I2A Institute. Additionally, he is an adjunct professor in the Department of Computer Science at Université de Sherbrooke.

His research interests include data mining, machine learning, recommender systems, social network analysis, and mobile computing.

The 5th edition of the workshop continues the tradition of bringing together researchers and practitioners to discuss data science solutions for societal challenges. Below are links to previous editions:

Past Workshops

The 5th edition continues the tradition of excellence in promoting research on equality, inclusion, and well-being through data science methodologies.