Skip to main navigation Skip to search Skip to main content

Does tone matter? Exploring context-aware explanations in route recommendations

  • Marloes Vredenborg*
  • , Marit Bentvelzen
  • , Christine Bauer
  • , Judtih Masthoff
  • *Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

Abstract

Recommendation algorithms support decision-making, yet their reasoning is often opaque. Explanations can improve user understanding, but the role of tone has received little attention, particularly in relation to situational context. This is especially relevant for route recommendations, where factors such as urgency shape travellers' needs. Using a mixed-method approach (focus groups, n = 15; validation study, n = 32; online experiment, n = 150), we examine how tone is perceived across contextual conditions in public transport. Unlike prior work comparing tone across domains and users, we focus on within-domain, situational context-dependent effects. Results show that situational context affects tone preferences. In urgent situations, humorous and empathetic tones are less appreciated than neutral or authoritative ones, and some tones are more context-sensitive than others. Our findings emphasise considering situational context when designing recommendation explanations, and offer guidance for designers and researchers.
Original languageEnglish
Pages30-39
Number of pages10
DOIs
Publication statusPublished - 7 Jun 2026
Event34th ACM International Conference on User Modeling, Adaptation and Personalization - Pedagogen, Gothenburg, Sweden
Duration: 8 Jun 202611 Jun 2026
Conference number: 34
https://www.um.org/umap2026/

Conference

Conference34th ACM International Conference on User Modeling, Adaptation and Personalization
Abbreviated titleUMAP 2026
Country/TerritorySweden
CityGothenburg
Period8/06/2611/06/26
Internet address

Bibliographical note

Publisher Copyright:
© 2026 Copyright held by the owner/author(s).

Keywords

  • explanations
  • tone
  • experiment
  • public transport
  • recommender systems

Fields of Science and Technology Classification 2012

  • 102 Computer Sciences
  • 501 Psychology

Cite this