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
A Comparative Empirical Study of Usability in AI-Generated and Human-Designed Web Interfaces
Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
2026 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

This thesis investigates perceived usability differences between selected AI-generated and human-designed landing pages. The study focuses on usability quality, communication clarity, trustworthiness, and perceived production readiness. A mixed-methods approach was used, combining a literature review, a survey with 51 participants, and 12 semi-structured interviews where participants reviewed two landing pages generated with Lovable and two publicly available production landing pages.

The findings show that the Lovable-generated landing pages were often perceived as visually modern, structured, and useful as starting points. However, participants also associated them with generic wording, unclear product communication, weaker credibility signals, and template-like layouts. The human-designed production pages were generally perceived as more mature, trustworthy, product-specific, and ready for real-world use.

The study concludes that AI-generated landing pages can support faster web design and early prototyping, but the findings should be interpreted carefully because the selected pages also differed in product maturity and business context. The results therefore show how these specific selected pages were perceived, rather than proving that all AI-generated interfaces are less usable than all human-designed interfaces.

Place, publisher, year, edition, pages
2026. , p. 36
Keywords [en]
generative AI, web interfaces, usability, landing pages, human-AI design
National Category
Software Engineering
Identifiers
URN: urn:nbn:se:bth-30234OAI: oai:DiVA.org:bth-30234DiVA, id: diva2:2085438
Subject / course
PA1445 Bachelor's Thesis in Software Engineering
Educational program
PAGWE Web Programming
Supervisors
Examiners
Available from: 2026-07-08 Created: 2026-07-08 Last updated: 2026-07-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Department of Software Engineering
Software Engineering

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 14 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