Date
Publisher
arXiv
Explanations are central to improving transparency, trust, and user satisfaction in recommender systems (RS), yet it remains unclear how different explanation formats (visual vs. textual) are suited to users with different personal characteristics (PCs). To this end, we report a within-subject user study (n=54) comparing visual and textual explanations and examine how explanation format and PCs jointly influence perceived control, transparency, trust, and satisfaction in an educational recommender system (ERS). Using robust mixed-effects models, we analyze the moderating effects of a wide range of PCs, including Big Five traits, need for cognition, decision making style, visualization familiarity, and technical expertise. Our results show that a well-designed visual, simple, interactive, selective, easy to understand visualization that clearly and intuitively communicates how user preferences are linked to recommendations, fosters perceived control, transparency, appropriate trust, and satisfaction in the ERS for most users, independent of their PCs. Moreover, we derive a set of guidelines to support the effective design of explanations in ERSs.
Study at a glance
- Question: How do visual and textual explanations and personal characteristics affect learners' perceptions of an educational recommender system?
- Setting and data: 54 adults aged 19 to 60 recruited from university networks in Germany, Pakistan, and Iran, evaluated during online sessions.
- Method: Mixed methods within-subject online user study comparing two explanation formats using tasks, surveys, and think-aloud interviews.
Why it matters
Explanations can improve trust, transparency, and satisfaction in educational recommender systems, yet how visual versus textual formats affect learners with different personal characteristics remains underexplored.
Key findings
- Visual explanations generated significantly higher trust (mean 5.64 versus 5.28) and satisfaction (mean 4.21 versus 4.01) than textual explanations.
- Perceived control and transparency did not differ significantly between visual and textual explanation formats.
- Visual explanations increased perceived control for highly agreeable users, and raised trust and satisfaction for conscientious users, while other personal traits showed no moderation effects.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
