Presentation
Perceived Failure Severity of Domestic Robots: Sentiment Analysis of Robotic Vacuum Reviews
SessionUX: Robots and AI
DescriptionWe examine how nonexpert users perceive the severity of robotic failures by studying vacuum robots as an exemplar of how domestic robots integrate into users’ homes. This work enhances the classification of robot failures using natural language processing models and statistical analysis. Utilizing a coded dataset of 8,306 online customer reviews of robotic vacuum cleaners (Honig et al., 2022), we applied RoBERTa (Liu et al., 2019), to assess each review's positivity, negativity, and neutrality. Analyses showed that failure category (technical, interaction, and service), review length, and star rating impacted the sentiments. The positive sentiment score decreased as the number of complaints in the review increased. Further, the presence of a failure event reduced the positive sentiment score. The impact of technical problems was the greatest. We discuss how sentiment analysis contributes to the understanding of perceived robot failure severity considering the robot’s role and interactivity.
Event Type
Industry/Practitioner Content
Lecture
UX Miniconference
TimeTuesday, October 14th3pm - 3:20pm CDT
LocationGrand Hall M/N
User Experience
UX Mini-Conference