Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

(Social) Trouble on the Road: Understanding and Addressing Social Discomfort in Shared Car Trips

Alexandra Bremers, Natalie Friedman, Sam Lee, Tong Wu, Eric Laurier, Malte Jung, Jorge Ortiz, Wendy Ju

TL;DR

The study addresses social discomfort during shared car trips and its safety implications by analyzing naturalistic video data from nine NYC-area families. It uses video interaction analysis to identify 116 social-discomfort moments and distills three mitigation strategies—Contextual Mediation, Social Mediation, and Social Support—for in-car interventions. The work discusses practical design implications for CUIs and LLMs, highlighting both potential benefits and current limitations of automated social interventions. It advocates for multi-modal, context-aware vehicle agents and urges caution about over-reliance on technology, given safety, cultural, and interpersonal considerations.

Abstract

Unpleasant social interactions on the road can negatively affect driving safety. At the same time, researchers have attempted to address social discomfort by exploring Conversational User Interfaces (CUIs) as social mediators. Before knowing whether CUIs could reduce social discomfort in a car, it is necessary to understand the nature of social discomfort in shared rides. To this end, we recorded nine families going on drives and performed interaction analysis on this data. We define three strategies to address social discomfort: contextual mediation, social mediation, and social support. We discuss considerations for engineering and design, and explore the limitations of current large language models in addressing social discomfort on the road.

(Social) Trouble on the Road: Understanding and Addressing Social Discomfort in Shared Car Trips

TL;DR

The study addresses social discomfort during shared car trips and its safety implications by analyzing naturalistic video data from nine NYC-area families. It uses video interaction analysis to identify 116 social-discomfort moments and distills three mitigation strategies—Contextual Mediation, Social Mediation, and Social Support—for in-car interventions. The work discusses practical design implications for CUIs and LLMs, highlighting both potential benefits and current limitations of automated social interventions. It advocates for multi-modal, context-aware vehicle agents and urges caution about over-reliance on technology, given safety, cultural, and interpersonal considerations.

Abstract

Unpleasant social interactions on the road can negatively affect driving safety. At the same time, researchers have attempted to address social discomfort by exploring Conversational User Interfaces (CUIs) as social mediators. Before knowing whether CUIs could reduce social discomfort in a car, it is necessary to understand the nature of social discomfort in shared rides. To this end, we recorded nine families going on drives and performed interaction analysis on this data. We define three strategies to address social discomfort: contextual mediation, social mediation, and social support. We discuss considerations for engineering and design, and explore the limitations of current large language models in addressing social discomfort on the road.
Paper Structure (29 sections, 3 figures, 6 tables)

This paper contains 29 sections, 3 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Defining discomfort in cars
  4. Capturing discomfort in cars
  5. Addressing discomfort in cars
  6. Approach
  7. Data collection
  8. Data analysis
  9. Findings
  10. High-level observations
  11. "Don't press your brake, dumbass!"
  12. "You look pale as a ghost"
  13. "Communicating my thought is so hard."
  14. Discussion
  15. How did participants address social discomfort?
  16. ...and 14 more sections

Figures (3)

  • Figure 1: Excerpt 1. Visual transcript of a driver reacting to a car suddenly braking in front.
  • Figure 2: Excerpt 2. Visual transcript of a compliment resulting in a squabble.
  • Figure 3: Excerpt 3. Visual transcript of a person getting repeatedly interrupted.