About

Jennifer Jenkins is a research social scientist and director at the Southwest Center at the University of Arizona. She holds advanced degrees in American literatures and cultures and Information Science. Her work focuses on the archival and community-based histories, literatures, and visual cultures of the Southwest and Mexico, with a particular emphasis on the cinema history of the region. Jenkins has been actively involved in curatorial projects, including the Puro Mexicano Tucson Film Festival, exhibits at the Arizona Historical Society, and the UA Museum of Art. She is the founder of Home Movie Day Tucson and the Tombstone Home Movie Project, which is part of an archive of amateur and locally-made films of the Arizona-Sonora borderlands. In 2011, she brought a digital archive of nearly 500 films by and about Native peoples of the Americas to the University of Arizona, engaging in Tribesourcing—reinterpreting midcentury educational and industrial films through Native community perspectives. Jenkins has received grants for her Tribesourcing Southwest Film Project from the NEH and is involved in initiatives to preserve and disseminate the arts, literatures, and visual cultures of the region. Her scholarly work includes numerous essays, book chapters, and monographs on genre film, Mexican cinema, and US and French literary film adaptations, as well as a cross-cultural analysis of moviegoing in the wartime Southwest.

Research topics

• Computer science
• Psychology
• Artificial intelligence
• Computer security
• Human–computer interaction

Selected publications

• Are You, You? Seamlessly Fighting Identity Fraud with Keystroke Dynamics

  Information Systems Research · 2026-03-04

  article

  PRACTICE-ORIENTED ABSTRACT In September of 2017, Equifax disclosed a data breach that exposed the personal information of 147 million people, including names, Social Security numbers, and addresses. Such high-profile data breaches have rendered traditional forms of identity verification—especially knowledge-based authentication (KBA)—worse than useless: fraudsters have a 92% success rate in KBA screenings, compared to just 46% for genuine customers. In the face of these challenges, digital platforms are turning to sparse alternative data sources and overt verification technologies, often to the detriment of the user experience. The objective of this research is to design and build a novel approach to identity verification for new platform users using digital behavior data—features that describe how users type and interact during account setup. The system (1) evaluates identity fraud risk for all first-time users, and (2) minimizes the impact on the new user experience by seamlessly analyzing behavior during a platform’s existing onboarding experience. We evaluated and improved the design in four experiments, culminating in an identity fraud detection tool that effectively detects identity fraud for first-time users and supports seamless user experiences.

  PublisherDOI

• From Clicks to Cognition: Detecting Thoughtful Engagement in Digital Surveys Through Behavioral Metrics

  Journal of the Association for Information Systems · 2025-12-14

  article1st authorCorresponding

  Ensuring the quality of self-reported survey data remains a persistent challenge in information systems (IS) research, particularly when respondents provide non-thoughtful answers that compromise data validity. Common detection methods--such as attention checks and overall survey duration--often fall short, as they are easily gamed or fail to reflect genuine cognitive engagement. To address these limitations, this study draws on the Metamemory framework to investigate whether fine-grained behavioral metrics can unobtrusively indicate cognitive engagement in an online survey and help identify non-thoughtful responses. In a controlled experiment, we found that respondents who thoughtfully engaged with the survey spent more time on each question, clicked more frequently, and exhibited greater cursor movement deviation. These metrics also show promise for use in predictive models to identify non-thoughtful responses. This research contributes to the IS field by linking metacognitive theory to online interaction behavior and advancing scalable methods for enhancing survey data integrity.

  Publisher

• Decomposing the Mouse Cursor: Empirically-Derived Multi-Dimensional Metrics for Predicting User Behavior and Engagement

  Journal of the Association for Information Systems · 2025-12-14

  article

  Tracking user behaviors and engagement through devices such as the computer mouse or keyboard has been used to predict important user outcomes, including cognitive conflict, product interest, and fraud, to name a few. For this, raw behavior data (e.g., xand y-position of the mouse cursor over time) is transformed into metrics (e.g., movement speed or deviation) to predict these outcomes. However, these classical features take each trial independently, overlooking higher-order links among users, stimuli, and behaviors. We introduce a Tensor-Enrichment Pipeline, applying Tucker, Higher-Order Singular Value Decomposition, and CANDECOMP/PARAFAC Decomposition, to extract five-dimensional user and cursor embeddings and append them to the original metrics. Using a random forest classifier, we compare baseline and enriched feature sets in a study (N=98) where participants’ buying decisions of 30 products were tracked. Tensor enrichments yield substantial gains: boosting accuracy from 35% to 69%, with higher recall and precision.

  Publisher

• Introduction to the Minitrack on Human-Computer Interaction

  ScholarSpace (University of Hawaii at Manoa) · 2025-12-23

  article1st authorCorresponding
  Publisher

• Introduction to the Minitrack on Human-Computer Interaction in the Digital Economy

  Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences · 2025-01-01

  articleOpen access
  PublisherOA PDFDOI

• The Fog of Warnings: How Non-Security-Related Notifications Diminish the Efficacy of Security Warnings

  MIS Quarterly · 2025-09-18 · 2 citations

  articleOpen accessSenior author

  Users’ disregard of security warnings is a critical problem in cybersecurity. This problem worsens when people confuse security warnings with common, non-security-related notifications, which they learn to routinely disregard. We investigate this problem through the neurobiological phenomenon of generalization of habituation, where habituation to one stimulus transfers to another stimulus that shares similar characteristics. Generalization of habituation suggests that because of habituation to frequent notifications, people may also be deeply habituated to security warnings they have never seen before, leading to warning disregard. Furthermore, because generalization of habituation occurs unconsciously at the neurobiological level, this may occur even though a person can consciously distinguish security warnings from notifications. We address this problem through three experiments—two in the field and one using functional magnetic resonance imaging. These experiments demonstrate how generalization of habituation occurs and can be mitigated by differentiating warnings from notifications in terms of their visual appearance or mode of interaction. These findings provide guidance to software developers for designing warnings that resist generalization of habituation and promote greater warning adherence.

  PublisherDOI

• Transforming Patient-Physician Interaction Through Asynchronous Online Health Interaction: A Relational Communication Perspective

  Journal of the Association for Information Systems · 2025-01-01 · 3 citations

  articleOpen accessSenior author

  Digital transformation integrates technology to modernize traditional processes. Asynchronous online health interactions (AOHIs) have revolutionized patient access to health information globally. Despite widespread AOHI implementation, few studies have thoroughly examined patient satisfaction or assessed the success of AOHI processes. This study, grounded in relational communication theory, introduces three fundamental dimensions for conceptualizing the success of AOHI process—interaction depth, information intensity, and relationship duration. It delves into the correlation between these key interaction factors and patient satisfaction. Additionally, the study identifies two distinctive characteristics of AOHI—provision of medical records and indirect interaction—as contingent elements influencing the proposed relationships. The research model developed, termed the “asynchronous online health interaction model,” underwent empirical testing using a robust dataset comprising 79,591 patient-physician interactions extracted from a prominent online healthcare platform. Results reveal that (1) interaction depth, information intensity, and relationship duration positively impact AOHI satisfaction, and (2) the provision of medical records and indirect interaction negatively moderate the effects of interaction depth and information intensity while amplifying the influence of relationship duration on AOHI satisfaction. This study significantly advances existing literature by providing a comprehensive conceptualization of the AOHI process. It highlights specific interaction behaviors and platform features pivotal for satisfaction and offers valuable insights for future healthcare research and practical applications, ultimately enhancing patient experience and healthcare delivery.

  PublisherOA PDFDOI

• Automated 3D Wound Segmentation Using UV Based Feature Extraction and Deep Learning

  2025-11-12

  article1st authorCorresponding

  Accurate 3D wound assessment is essential for effective clinical decision-making, but obtaining annotated wound datasets remains challenging due to privacy concerns and the labor-intensive nature of manual labeling. This study introduces a 3D wound segmentation framework that leverages simulated wound data generated via 3D scanning and advanced generative techniques. By utilizing the 2D UV-mapped texture of 3D wound surfaces, the system enables precise segmentation with deep learning methods. Specifically, we used the U-Net architecture, a widely adopted model for medical image segmentation. This proposed system offers a promising alternative to traditional 2D image and 3D volume segmentation, paving the way for improved medical imaging workflows using simulated data and multi-dimensional analysis.

  PublisherDOI

• Enabling Product Platform Growth with AI-Assisted Insight

  Progress in IS · 2025-01-01

  book-chapter1st authorCorresponding
  PublisherDOI

• Detecting Social Desirability Bias with Human-Computer Interaction: A Mouse-Tracking Study

  Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences · 2024-01-01 · 2 citations

  articleOpen access

  Social desirability bias undermines self-report accuracy, necessitating novel approaches to detect and mitigate its impact. This study aimed to investigate the influence of social desirability on questionnaire responses by analyzing mouse cursor movements and answering behaviors. Respondents (n=238) completed a health and wellness questionnaire while their mouse cursor data was recorded. The results revealed that individuals under a higher social desirability treatment exhibited significantly longer response times and slower mouse cursor speeds, supporting the hypothesis that they may engage in more cautious and deliberate responding. However, no significant differences were found in terms of mouse cursor deviations or answer switches between the two groups. These findings suggest that analyzing mouse cursor movements can provide valuable insights into the influence of social desirability bias on questionnaire responses, offering a potentially scalable method for detection and future intervention.

  PublisherOA PDFDOI

Frequent coauthors

• Harold Szu

  58 shared

• Joseph S. Valacich

  University of Arizona

  42 shared

• M. Okan İrfanoğlu

  National Institute of Biomedical Imaging and Bioengineering

  21 shared

• Anthony Vance

  21 shared

• Elizabeth Hutchinson

  21 shared

• Bonnie Brinton Anderson

  Brigham Young University

  19 shared

• C. Brock Kirwan

  Brigham Young University

  19 shared

• Aaron F. Zimbelman

  University of South Carolina

  16 shared

Awards & honors

• 2017 NEH Humanities Collections and Reference Resources Gran…
• 2022 NEH Digital Humanities Advancement Grant
• CUES Distinguished Fellow (2024)