Visual or Textual: Effects of Explanation Format and Personal Characteristics on the Perception of Explanations in an Educational Recommender System
HCI Today summarized the key points
- •This article reports research comparing how visual versus textual explanation formats affect users’ perceptions in an educational recommender system.
- •In a user study with 54 participants, the researchers directly compared visual and textual explanations that conveyed the same information.
- •The results showed similar levels of perceived control and transparency, but visual explanations received higher ratings for trust and satisfaction.
- •Most individual characteristics—such as personality, need for cognition, familiarity with visualization, and technical expertise—did not substantially change the effect of explanation format.
- •The study suggests that easy-to-understand, interactive visual explanations are beneficial for most users and that design guidelines are needed.
This summary was generated by an AI editor based on HCI expert perspectives.
Why Read This from an HCI Perspective
This article treats explanation design in recommender systems not as a simple question of whether to ‘show or tell,’ but as an HCI challenge that must be addressed together with users’ individual differences. In particular, in the context of educational ERS, it empirically compares how visual and textual explanations affect trust, satisfaction, and a sense of control, providing meaningful guidance for refining design criteria for explanation interfaces. For practitioners, it offers actionable implications; for researchers, it provides evidence for validating explanation adaptation based on individual differences.
CIT's Commentary
From a CIT perspective, the core contribution of this study is that it prompts a re-examination of the direction of ‘personalized explanations.’ Many systems branch explanations in fine detail based on user characteristics, but this work suggests that, at least in educational recommendation contexts, well-designed visual explanations may be reliably beneficial for most users. In other words, before overly segmenting users, the first priority is to get the information structure right—guiding attention, maintaining color consistency, and reducing interaction costs. That said, because this is an online experiment with n=54, contextual dependence remains, and the long-term effects of using explanations during real learning tasks still need to be verified separately. CIT views these findings not as a simplistic conclusion that ‘visual is better,’ but as a starting point for articulating minimal design principles that enhance the interpretability of explanations.
Questions to Consider While Reading
- Q.In educational recommendation contexts, how can we verify whether the advantage of visual explanations carries through to long-term usage and actual learning outcomes?
- Q.If meaningful moderating effects of individual differences were limited, what user characteristics or situational variables should be considered next?
- Q.Rather than comparing visual and textual explanations as a binary, what conditions would make mixed-format explanations the most effective?
This commentary was generated by an AI editor based on HCI expert perspectives.
Please refer to the original for accurate details.
Subscribe to Newsletter
Get the weekly HCI highlights delivered to your inbox every Friday.