The ACM CHI (pronounced ‘kai’) Conference on Human Aspects in Computing Systems is the foremost event for Human-Computer Interaction (HCI) research. TRI was thrilled to be a contributing sponsor for CHI’s 2023 hybrid conference in Hamburg, Germany, April 23–28.

Constructing off of TRI’s successful showing at CHI 2022, our researchers at CHI 2023 presented talks on three full papers and a poster on one late-breaking work. .

At TRI, our research is concentrated on amplifying human ability and making our lives safer and more sustainable. In that very same vein, our research accepted at CHI this 12 months focused on how we will expand human understanding, leverage AI to assist people make higher decisions, and speed up the shift to carbon neutrality. Listed here are the areas of research that we covered on the conference:

Vikram Mohanty, Alexandre L. S. Filipowicz, Nayeli Suseth Bravo, Scott Carter, David A. Shamma

There may be a growing interest in eco-feedback interfaces that display environmental impact information for various services and products. On this , we examine the effectiveness of various carbon-based eco-feedback interventions — including direct CO2 emissions, simpler heuristic interventions, and more relatable CO2-equivalent activities — within the context of non-public transportation decisions. We explore the influence of emission information on vehicular decisions and examine how displaying CO2 emissions information, CO2 equivalencies, and other data might help people select eco-friendly ride-sharing options.

Our studies focused on how people navigated each ride-hailing and car-rental decisions. In each scenarios, participants picked between regular and eco-friendly options. Our surveys tested different equivalencies, social features, and valence-based interventions. We found that participants usually tend to select green rides when presented with additional details about emissions; representing options with CO2 by weight was found to be essentially the most effective. Moreover, we found that information framing — be it individual or collective footprint and positive or negative valence — had an impact on participants’ decisions.

Paul D. S. Fink, Velin Dimitrov, Hiroshi Yasuda, Tiffany L. Chen, Richard R. Corey, Nicholas A. Giudice, Emily Sarah Sumner

This focuses on the potential advantages of fully autonomous vehicles (FAVs) for people who find themselves blind and visually impaired (BVI) and the way FAVs could improve their independence and autonomy. We argue that BVI people will even desire some level of control over the FAVs they use, including personalizing the vehicle’s driving style and changing the route. To realize this level of control, we propose using mid-air gestural systems, which could be performed without the guiding use of vision and offer significant hygienic benefits within the context of shared FAVs. We conducted a needs assessment and user study involving BVI participants to discover the kinds of vehicle control which might be essential to this demographic and the situational information crucial to be conveyed and to design a mid-air gestural system to advertise multisensory control. The resulting experimental interface combines ultrasound-based haptic representations of the driving environment, queryable spatialized audio descriptions, and mid-air gestures to mediate between the 2. The system is designed to serve each BVI individuals who have previously operated traditional vehicles in addition to individuals who have never driven before, representing broad and inclusive usability across the spectrum of vision loss.

Matthew L. Lee, Scott Carter, Rumen Iliev, Nayeli Suseth Bravo, Monica P. Van, Laurent Denoue, Everlyne Kimani, Alexandre L. S. Filipowicz, David A. Shamma, Kate A. Sieck, Candice Hogan, Charlene C. Wu

Reducing driving-related carbon emissions is crucial for meeting climate goals, and switching to battery electric vehicles (BEVs) is one solution. Nonetheless, there are challenges to the widespread adoption of BEVs within the US, including high purchase prices, limited charging infrastructure, and range anxiety. Plug-in hybrid electric vehicles (PHEVs) are a viable alternative to BEVs, as they’ll reduce carbon emissions while still using an internal combustion engine (ICE) for longer trips. PHEVs even have smaller batteries than BEVs, making them cheaper and requiring fewer resources to provide. Nonetheless, the effectiveness of PHEVs in reducing emissions is determined by driver behavior, as they must be charged commonly to electrically power a big proportion of miles driven. On this , we conducted a mixed-methods study to grasp PHEV owners’ charging habits. We found that charging is well supported at home, but that away-from-home charging is difficult resulting from a scarcity of accessible chargers, broken chargers, hard-to-find chargers, and high costs. We tested quite a few concepts to grasp and address these issues. Overall, we found that while PHEVs have the potential to significantly reduce driving-related carbon emissions, further research and infrastructure improvements are needed to totally realize this potential.

Francine Chen, Matthew K. Hong, Laurent Denoue, Kate S. Glazko, Emily Sarah Sumner, Yan-Ying Chen, Matthew Klenk

Creating a totally labeled dataset from short free-text responses could be difficult and time-consuming. Past work has used a greedy method for coding text, but it might probably end in neglected themes. On this we explain our solution to this issue with the event of a recent, interactive, non-greedy approach called CodeML that uses machine learning to help human coders in identifying a code set. CodeML proposes groups of comparable concepts as codes to cut back the opportunity of overlooking themes and requires human input to guide the choice and definition of codes. Our evaluation shows that CodeML outperformed a well-liked industrial product in identifying codes at a finer level for a deeper understanding of the dataset.