Violeta Rodriguez Palacios

<ul><li>Health Equity&nbsp;</li><li>Parenting</li><li>Family Dynamics</li><li>Psychometrics and Measurement</li><li>Developmental Psychopathology</li><li>Artificial Intelligence</li><li>Natural Language Processing</li><li>Human–AI Interaction</li></ul> <div> <div> <div> <p><strong>Dr. Rodriguez is accepting applications for graduate students to join her lab as a primary research advisor beginning Fall 2025. She will be considering applicants to both the Ph.D. program in Clinical-Community Psychology and the M.S. program in Psychological Science.</strong></p> <p>My research focuses on understanding the mechanisms that contribute to, maintain, and exacerbate health disparities among minoritized youth and families. My work centers on developing psychometrically robust, culturally responsive, and scalable approaches to assessing parenting and youth mental health in diverse contexts. My research program advances three major aims, unified by the goal of improving health outcomes for underserved populations globally (e.g., Global South countries, racially and ethnically minoritized communities, immigrant families, Spanish-speaking caregivers and youth, LGBTQIA+ families, and families disproportionately affected by chronic illness).</p> <p>First, I examine causal and perpetuating factors that drive disparities in youth and family mental health using developmental, ecological, and intensive longitudinal approaches.</p> <p>Second, a central pillar of my program, and the focus of my DP5, is the advancement of innovative, contextually grounded measurement science. I integrate psychometric modeling (e.g., IRT, explanatory IRT, latent variable modeling), qualitative methods, and emerging computational tools to create and validate assessments with strong cross-cultural and contextual validity. This work increasingly incorporates AI-assisted methodologies and natural language processing (NLP), including automated text analysis of qualitative interviews, computational item development, and NLP-based detection of parenting and emotional processes.</p> <p>In addition to psychometric innovation, I collaborate extensively with researchers in human–AI interaction, natural language processing, and computational social science to examine how AI can support mental health measurement and intervention, including on current NIH funded work with caregivers. These collaborations allow my lab to integrate AI, NLP, and human–computer interaction methods with traditional developmental and clinical research to create more precise, ethical, and culturally informed tools for assessment and intervention.</p> <p>Finally, I focus on translating evidence-based health promotion strategies and interventions into underserved settings using community-based participatory research (CBPR) principles and implementation science frameworks (e.g., MOST, CFIR). My work increasingly examines how AI-enhanced measurement and decision-support tools can support equitable intervention delivery, reduce burdens on community providers, and improve access to culturally responsive care.</p> </div> </div> </div>

<p>Finley, J. C. A., Robinson, A. D., Soble, J. R., &amp; Rodriguez, V. J. (2026). Using machine learning to detect noncredible cognitive test performance. <em>Clinical Neuropsychologist</em>, <em>40</em>(3), 830-847. <a href="https://doi.org/10.1080/13854046.2024.2440085" class="link">https://doi.org/10.1080/13854046.2024.2440085</a></p><p>Rodriguez, V. J., Finley, J. C. A., Liu, Q., Alfonso, D., Basurto, K. S., Oh, A., Nili, A., Paltell, K. C., Hoots, J. K., Ovsiew, G. P., Resch, Z. J., Ulrich, D. M., &amp; Soble, J. R. (2026). Empirically derived symptom profiles in adults with attention-Deficit/hyperactivity disorder: An unsupervised machine learning approach. <em>Applied Neuropsychology: Adult</em>, <em>33</em>(1), 209-218. <a href="https://doi.org/10.1080/23279095.2024.2343022" class