About

Ivon Arroyo is a professor at the Manning College of Information & Computer Sciences at the University of Massachusetts Amherst, specializing in learning sciences, computer science, and educational/cognitive psychology. Her expertise includes designing novel technologies for learning and assessment targeted at K-12 students studying mathematics. She has served as principal investigator or co-principal investigator on more than 20 research projects supported by organizations such as the National Science Foundation, the Institute of Education Sciences, the Gates Foundation, and seed funding from UMass Amherst. Her research includes the development of innovative math games using wearable technology, exemplified by her NSF CAREER award project involving cell-phone embodied math games called WearableLearning, which integrates mathematics into real-world objects and environments. Arroyo's work also explores mathematical game creation by students to foster computational thinking skills, as well as ethics education for computer science students through immersive online scenarios. With over 20 years of experience in STEM learning software research and development, Arroyo has contributed to the creation and management of educational software such as MathSpring.org, which contains a large database of math problems aligned with standards and tailored to multilingual students, including Spanish speakers. Her efforts have included localizing software for specific cultural contexts, such as Puerto Rican Spanish and Argentine education settings, with positive impacts on math learning and student engagement. Arroyo has been actively involved in service to the research community as an editorial board member, reviewer, and NSF grant proposal panelist. She has authored or co-authored over 100 publications, received multiple awards including a NSF CAREER award in 2014 and Best Paper awards at prominent conferences, and was awarded a Fulbright Masters Program Fellowship in 1997. Her primary research lab is the Advanced Learning Technologies lab at UMass Amherst.

Research topics

• Computer Science
• Artificial Intelligence
• Human–computer interaction
• Psychology
• Social psychology
• Mathematics education
• Machine Learning
• Data science
• Cognitive psychology
• Pedagogy
• Multimedia

Selected publications

• Understanding Users' Privacy Reasoning and Behaviors During Chatbot Use to Support Meaningful Agency in Privacy

  arXiv (Cornell University) · 2026-01-26

  preprintOpen accessSenior author

  Conversational agents (CAs) (e.g., chatbots) are increasingly used in settings where users disclose sensitive information, raising significant privacy concerns. Because privacy judgments are highly contextual, supporting users to engage in privacy-protective actions during chatbot interactions is essential. However, enabling meaningful engagement requires a deeper understanding of how users currently reason about and manage sensitive information during realistic chatbot use scenarios. To investigate this, we qualitatively examined computer science (undergraduate and masters) students' in-the-moment disclosure and protection behaviors, as well as the reasoning underlying these behaviors, across a range of realistic chatbot tasks. Participants used a simulated ChatGPT interface with and without a privacy notice panel that intercepts message submissions, highlights potentially sensitive information, and offers privacy protective actions. The panel supports anonymization through retracting, faking, and generalizing, and surfaces two of ChatGPT's built-in privacy controls to improve their discoverability. Drawing on interaction logs, think-alouds, and survey responses, we analyzed how the panel fostered privacy awareness, encouraged protective actions, and supported context-specific reasoning about what information to protect and how. We further discuss design opportunities for tools that provide users greater and more meaningful agency in protecting sensitive information during CA interactions.

  PublisherDOI

• Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agents

  ArXiv.org · 2026-03-19

  articleOpen accessSenior author

  Supporting users in protecting sensitive information when using conversational agents (CAs) is crucial, as users may undervalue privacy protection due to outdated, partial, or inaccurate knowledge about privacy in CAs. Although privacy knowledge can be developed through standalone resources, it may not readily translate into practice and may remain detached from real-time contexts of use. In this study, we investigate in-context, experiential learning by examining how interactions with privacy tools during chatbot use enhance users' privacy learning. We also explore interface design features that facilitate engagement with these tools and learning about privacy by simulating ChatGPT's interface which we integrated with a just-in-time privacy notice panel. The panel intercepts messages containing sensitive information, warns users about potential sensitivity, offers protective actions, and provides FAQs about privacy in CAs. Participants used versions of the chatbot with and without the privacy panel across two task sessions designed to approximate realistic chatbot use. We qualitatively analyzed participants' pre- and post-test survey responses and think-aloud transcripts and describe findings related to (a) participants' perceptions of privacy before and after the task sessions and (b) interface design features that supported or hindered user-led protection of sensitive information. Finally, we discuss future directions for designing user-facing privacy tools in CAs that promote privacy learning and user engagement in protecting privacy in CAs.

  PublisherOA PDF

• Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agents

  arXiv (Cornell University) · 2026-03-19

  preprintOpen accessSenior author

  Supporting users in protecting sensitive information when using conversational agents (CAs) is crucial, as users may undervalue privacy protection due to outdated, partial, or inaccurate knowledge about privacy in CAs. Although privacy knowledge can be developed through standalone resources, it may not readily translate into practice and may remain detached from real-time contexts of use. In this study, we investigate in-context, experiential learning by examining how interactions with privacy tools during chatbot use enhance users' privacy learning. We also explore interface design features that facilitate engagement with these tools and learning about privacy by simulating ChatGPT's interface which we integrated with a just-in-time privacy notice panel. The panel intercepts messages containing sensitive information, warns users about potential sensitivity, offers protective actions, and provides FAQs about privacy in CAs. Participants used versions of the chatbot with and without the privacy panel across two task sessions designed to approximate realistic chatbot use. We qualitatively analyzed participants' pre- and post-test survey responses and think-aloud transcripts and describe findings related to (a) participants' perceptions of privacy before and after the task sessions and (b) interface design features that supported or hindered user-led protection of sensitive information. Finally, we discuss future directions for designing user-facing privacy tools in CAs that promote privacy learning and user engagement in protecting privacy in CAs.

  PublisherDOI

• Understanding Users' Privacy Reasoning and Behaviors During Chatbot Use to Support Meaningful Agency in Privacy

  ArXiv.org · 2026-01-26

  articleOpen accessSenior author

  Conversational agents (CAs) (e.g., chatbots) are increasingly used in settings where users disclose sensitive information, raising significant privacy concerns. Because privacy judgments are highly contextual, supporting users to engage in privacy-protective actions during chatbot interactions is essential. However, enabling meaningful engagement requires a deeper understanding of how users currently reason about and manage sensitive information during realistic chatbot use scenarios. To investigate this, we qualitatively examined computer science (undergraduate and masters) students' in-the-moment disclosure and protection behaviors, as well as the reasoning underlying these behaviors, across a range of realistic chatbot tasks. Participants used a simulated ChatGPT interface with and without a privacy notice panel that intercepts message submissions, highlights potentially sensitive information, and offers privacy protective actions. The panel supports anonymization through retracting, faking, and generalizing, and surfaces two of ChatGPT's built-in privacy controls to improve their discoverability. Drawing on interaction logs, think-alouds, and survey responses, we analyzed how the panel fostered privacy awareness, encouraged protective actions, and supported context-specific reasoning about what information to protect and how. We further discuss design opportunities for tools that provide users greater and more meaningful agency in protecting sensitive information during CA interactions.

  PublisherOA PDF

• IMPROVING STUDENT ENGAGEMENT WITH THE MATHSPRING INTELLIGENT TUTORING SYSTEM: A REINFORCEMENT LEARNING APPROACH

  EDULEARN proceedings · 2025-06-01

  articleSenior author
  PublisherDOI

• Embedding Ethical Awareness in Computer Science and AI Education: The PEaRCE Approach to Responsible Computing

  Lecture notes in computer science · 2025-01-01

  book-chapterSenior author
  PublisherDOI

• The Role of Educational Technology in K-12 STEM: A Qualitative Multi-stakeholder Study on Technology Integration

  Lecture notes in educational technology · 2025-01-01

  book-chapter
  PublisherDOI

• AI-Powered Math Learning: Evaluating the Impact of a Personalized Tutoring Platform that Responds to Affect

  Communications in computer and information science · 2025-01-01

  book-chapter
  PublisherDOI

• Comparing the Effectiveness of Digital Game-Based Learning and Embodied Learning

  Communications in computer and information science · 2025-01-01

  book-chapter
  PublisherDOI

• Grand Challenges in AI and Education Beyond 2030

  Interaction design & architecture(s)/ID&A Interaction design & architecture(s) · 2025-05-31

  articleOpen access

  Artificial intelligence (AI) has made large changes in major industries and disrupted or reorganized many disciplines. As a result, traditional educational practices need to be reexamined to enable learners to develop new skills, to manage and utilize new technologies and to increase productivity in a rapidly changing world. A more flexible educational system is required to enable life-long and life-wide upskilling and reskilling. This article provides four grand challenges for AI and education to optimize digital learning, online resources and virtual classrooms. It suggests several problems to address, visions to spur the field forward and strategies that will make teaching and learning more effective. The article also considers ethical use of technology, decreased jobs in some sectors and the possibility that AI will exacerbate an existing deficit in diversity and equity among students.

  PublisherDOI

Recent grants

• (GSE/RES) What kind of Math Software works for Girls? The effectiveness of motivational and cognitive interventions

  NSF · $450k · 2007–2010

• CAREER: Wearable Tutors in the Embodied Mathematics Classroom

  NSF · $597k · 2017–2020

• CAREER: Wearable Tutors in the Embodied Mathematics Classroom

  NSF · $483k · 2020–2023

• INT: Collaborative Research: Detecting, Predicting and Remediating Student Affect and Grit Using Computer Vision

  NSF · $760k · 2016–2020

• EAGER: Teaching Computational Thinking through Programming Wearable Devices as Finite State Machines

  NSF · $316k · 2016–2019

Frequent coauthors

• Beverly Park Woolf

  81 shared

• Winslow Burleson

  University of Arizona

  26 shared

• Kasia Müldner

  19 shared

• Danielle Allessio

  19 shared

• Tom Murray

  Graphcore (United Kingdom)

  14 shared

• Carole R. Beal

  University of Florida

  13 shared

• David G. Cooper

  Butler University

  13 shared

• Francisco Enrique Vicente Castro

  New York University

  11 shared

Education

• Ed. D., Education

  University of Massachusetts Amherst

  2003

• M.S., Computer Science

  University of Massachusetts Amherst

  2000

• Licenciada en Informatica, Computer Science

  Universidad Blas Pascal

  1995

Awards & honors

• NSF CAREER Award (2014)
• Best Paper Award at the International Conference on Educatio…
• Best Paper Award at the International Conference on Artifici…
• Fulbright Masters Program Fellowship (1997)