Research

Embodied AI, Agentic Systems, and Human-Centered Technology

Memory architectures for embodied agents, with a parallel thread in digital well-being and privacy in social computing

Overview

My research spans embodied AI, agentic memory systems, and human-centered technology—work grounded in over fifteen years of software and systems engineering across defense simulation and cloud computing. I am especially interested in memory architectures for embodied agents, including device-agnostic experience memory that decouples learned knowledge from the hardware it runs on.

A parallel track examines digital well-being, privacy behavior, and social computing: how people navigate disclosure and well-being in digital environments, informed by computational psycholinguistics, large language models, and neuropsychological and sociocultural influences on human-computer interaction.

Publications

Social Computing

Unveiling Influencer-Driven PII Disclosures in Social Media Discourse

Privacy

E. J. Rosado, L. Wang, L. P. Dringus, & J. Sun

Digital Transformation and Society, 2026

This study investigates how social media influencers drive personally identifiable information (PII) disclosures in online discourse, examining the patterns and implications of privacy-related content sharing in influencer networks.

The Adaptive PERMA Framework: Reconceptualizing Well-Being as Dynamic and Context-Responsive

E. J. Rosado

Open Science Foundation, 2026

Proposes an adaptive PERMA framework that reconceptualizes well-being as dynamic and context-responsive, extending positive psychology constructs for contemporary digital and social environments.

Privacy vs. Social Capital: Examining Information Disclosure Patterns Within Social Media Influencer Networks

Privacy

E. J. Rosado

ProQuest Dissertations Publishing, 2024

Doctoral dissertation examining the trade-offs between privacy and social capital in social media influencer networks, analyzing how information disclosure patterns affect network dynamics and individual privacy behaviors.

Privacy & Security

When Parametric Knowledge Wins: A Controlled Ablation of Agent Skills and Tool Use for PII Detection in Small Language Models

Privacy ML

E. J. Rosado

Transactions on Machine Learning Research, 2026 — review in progress

A controlled ablation study comparing agent skills and tool use against parametric knowledge for PII detection in small language models, examining when each approach is most effective.

PII-Codex: a Python library for PII detection, categorization, and severity assessment

Privacy Data

E. J. Rosado

Journal of Open Source Software, 8(86), Article 5402, 2023

PII-Codex is an open-source Python library designed for comprehensive personally identifiable information detection, categorization, and severity assessment in text data, providing researchers and practitioners with tools for privacy-preserving data analysis.

Concentrations

Privacy Engineering

Examining psychological and social factors affecting information disclosure patterns, privacy behaviors, and privacy-averse actions in digital environments.

Human-Computer Interaction

Exploring how cognitive processes and social contexts shape the way people interact with technology, including collaborative design and user experience.

Social Computing

Studying social dynamics, community interactions, and collective behavior in online platforms and digital social environments.

Embodied AI & Agentic Memory

Designing memory architectures and agentic systems for embodied platforms—decoupling learned experience from specific hardware so agents can operate across robots, edge devices, and simulation.

Get in Touch

Interested in collaborating on research or discussing my work? I'm always open to connecting with fellow researchers, students, and industry professionals.