Robots, personal safety, and moving to learn: faculty research is far-reaching
September 16, 2021
Would you accept a robot telling your children bedtime stories?
In recent publications, human-computer interaction faculty and students from the IU School of Informatics and Computing at IUPUI are exploring how technology intersects with:
- Artificial intelligence—analyzing parental acceptance of children’s storytelling robots
- Domestic abuse—the role tech plays in how Saudi women recognize and manage abuse, and seek non-abusive futures
- Movement and data—interpreting data using gestures and body movements
AI and bedtime stories
In their paper “Parental Acceptance of Children’s Storytelling Robots: A Projection of the Uncanny Valley of AI,” an alumna and faculty members from the School of Informatics and Computing examined parents’ acceptance of this new technology.
Parents used robots to tell stories to their children. Then parents were interviewed about their child’s story time, whether they used any technology, and what they envisioned future storytelling robots might be like.
Many parents valued in-person storytelling as a time to bond with their children, and worried that a storytelling robot wouldn’t be able to interact and answer questions. But some acknowledged a bedtime story surrogate might be handy (especially when a weary parent’s “The end” is met with a toddler’s emphatic “Read it again!”)
Robots that appeared more human could make some parents feel uneasy, edging into the uncanny valley of AI, perhaps because they act sociable without really understanding themselves or others.
The paper’s authors include Chaolan Lin, an alumnus of the SOIC Master of HCI program who is now pursuing her Ph.D. at the University of California San Diego. Other authors: Lynn Dombrowski, Andrew Miller, Erin Brady, and Karl F. MacDorman, all faculty of the IU School of Informatics and Computing at IUPUI, and Selma Šabanović of IU’s Luddy School of Informatics, Computing, and Engineering in Bloomington. The paper was published in Frontiers of Robotics and AI.
Technology and domestic violence
The United Nations estimates that globally, almost one in three women have been subjected to intimate partner violence, non-partner sexual violence, or both.
More than a third of Arab women experience domestic abuse in their lifetime, the UN estimates. IUPUI researchers asked Saudi women about their practices in response to domestic abuse and how they use technology to navigate domestic safety concerns. They learned how social media and platforms, such as Snapchat, WhatsApp, and direct messaging, offer private ways to engage with other women and seek advice.
The cost of breaking away from abusive situations is high, due to cultural and social expectations, unpredictability and scarcity of public services, and policy constraints. Thus, women may decide to manage, rather than leave, an abusive situation. They use technology to keep up with personal and professional networks, and with laws and policies; for self-improvement; to remain employable; and to develop resiliency and self-esteem.
Messaging and ride-share apps allowed women to quickly communicate concerns about their safety to friends or relatives, or to arrange to leave the home.
To support these needs, the researchers noted that designing technologies which recognize non-Western religious and cultural values can help to empower women as they navigate how to manage domestic abuse.
Their paper, “Daughters of Men: Saudi Women’s Sociotechnical Agency Practices in Addressing Domestic Abuse,” received an honorable mention at CSCW 2020, a top-tier venue for HCI research. The paper appeared in the Proceedings of the ACM on Human-Computer Interaction and was written by Hawra Rabaan, IUPUI doctoral student; Lynn Dombrowski, associate professor, human-computer interaction, IU School of Informatics and Computing at IUPUI; and Alyson L. Young, former assistant professor, IU School of Informatics and Computing at IUPUI.
Data and movement
In “Show Me How You Interact, I Will Tell You What You Think: Exploring the Effect of the Interaction Style on Users’ Sensemaking about Correlation and Causation in Data,” researchers studied how people interpreted data through movement.
As we produce more data than ever before, they note, data exploration and visualization have become increasingly important. For example, museums can offer new ways for visitors to explore through interactive displays controlled by gestures and body movements.
In the study, participants interacted with 3D globes representing geo-referenced data on a 65-inch screen. The “full body” group was able to control data visualization using mid-air gestures and body movements. The other group used a Gamepad joystick device.
The researchers discovered the groups that controlled their interactions using gestures and body movements interpreted the data differently than the GamePad group.
These findings suggest that our whole body (not just our eyes) plays an important role in how we make sense of data when we interact with data visualizations. Specific gestures may play an important role in building reasoning about data.
Published at the 2021 Designing Interactive Systems Conference, the paper’s authors are Milka Trajkova, research assistant, IU School of Informatics and Computing at IUPUI; Francesco Cafaro, assistant professor, human-computer interaction, IU School of Informatics and Computing at IUPUI; and A’aeshah Alhakamy, Computers and Information Technology University of Tabuk, Saudi Arabia.