Date of Award

Spring 2026

Document Type

Open Access Thesis

Department

Computer Science and Engineering

First Advisor

Yan Tong

Abstract

As images have become a critical strategy for hospitality businesses to position and differentiate their brands online, and brand personality projected by brands and perceived by prospective consumers has been recognized as a key factor influencing booking decisions, this thesis investigates an understudied area: how brand personality perceived from hotel images can be automatically assessed using advanced computational models.

Specifically, this study systematically compares four model architectures (i.e., YOLO26 Nano, ResNet50, Swin-Small Transformer, and CLIP) across multiple label sources, including human rater annotations, labels generated by a single large language model (LLM) (GPT-4o), and average labels generated by multiple LLMs (GPT-4o, Gemini 2.5 Flash, and Claude Sonnet 4.6). A dataset of 2,182 hotel-generated images posted on a social media platform was annotated and evaluated across six brand personality dimensions: relaxing, hospitable, lively, distinctive, sophisticated, and wholesome.

The results demonstrate that CLIP, trained on multi-LLM averaged labels, achieves the highest performance, outperforming all image-only architectures when evaluated on LLM-generated labels. However, the well-performing model fails to predict human perceptions when testing on human labels. This study contributes to a deeper understanding of how affective semantics related to brand personality perception can be effectively recognized by comparing different deep learning models across different label  sources. It further extends the discussion on whether LLM-generated labels can replace human judgement in contexts that require domain knowledge and higher-level semantic interpretation.

Rights

© 2026, Ningqiao Li

Download

Available for download on Wednesday, May 31, 2028

Share

COinS