Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Vakna med AI: design av interaktiv onboarding för röstbaserade alarm
Blekinge Institute of Technology, Faculty of Computing, Department of Technology and Aesthetics.
2026 (Swedish)Independent thesis Basic level (degree of Bachelor), 20 credits / 30 HE creditsStudent thesis
Abstract [sv]

Detta arbete undersöker hur guidad onboarding, baserad på principen learning by doing, kan påverka användarens förståelse och användning av AI-genererade röstfunktioner i en mobil alarmapplikation. Studien utgår från WiseRise, en prototyp där användaren kan ange personliga mål och få AI-genererade röstmeddelanden upplästa som morgonalarm. För att undersöka den guidade onboardingens påverkan, designades ett onboardingflöde där användaren introduceras till funktioner genom aktiv användning och stegvis interaktion. Studien genomfördes genom A/B test där deltagarna testade applikationen med och utan onboarding samt besvarade en enkät om förståelse och användarupplevelse. Resultatet visar att onboarding kan bidra till tydligare förståelse, men att viss osäkerhet kring funktionernas syfte fortfarande kvarstod. Studien bidrar med kunskap kring design av onboarding för en applikation med AI-funktioner.

Abstract [en]

This study explores how guided onboarding, based on the principle of learning by doing, can influense users understanding and use of AI-generated voice features in a mobile alarm application. The study is based on WiseRise, a prototype where users can set personal goals and receive AI-generated voice messages as a morning alarm. To examine how onboarding may influence the first-time user experience, an interactive onboarding flow was developed where users were introduced to features through active and step by step interaction. The study was conducted through an A/B test in which participants tested the application with and without onboarding and completed a questionnaire regarding understanding and user experience. The result indicates that onboarding can contribute to clearer understanding, although some uncertainty regarding the purpose of the features still remained. The study contributes knowledge regarding the design of onboarding for applications with AI-based features.

Place, publisher, year, edition, pages
2026. , p. 22
Keywords [sv]
Guidad onboarding, learning by doing, AI-genererade röster, användarupplevelse, mobilapplikation, användarförståelse, kognitiv belastningsteori.
National Category
Other Engineering and Technologies
Identifiers
URN: urn:nbn:se:bth-30153OAI: oai:DiVA.org:bth-30153DiVA, id: diva2:2084056
Subject / course
ME1659 Bachelor Thesis in Media Technology
Educational program
MEGDP Digital Visual Production
Supervisors
Examiners
Available from: 2026-07-03 Created: 2026-07-03 Last updated: 2026-07-03Bibliographically approved

Open Access in DiVA

fulltext(995 kB)2 downloads
File information
File name FULLTEXT01.pdfFile size 995 kBChecksum SHA-512
6e3f65ef60cef92a89020011ba2756f814830b3b743523287624c45bf3d94e45bd2d05d3afe91f6d873a090d29abf2753d42cf225be54ffc00ca4b588c2635d2
Type fulltextMimetype application/pdf

By organisation
Department of Technology and Aesthetics
Other Engineering and Technologies

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 15 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf