Evaluating embedding models for text classification in apartment management

The recent proliferation of embedding models has enhanced the accessibility of textual data classification. However, the crucial challenge is evaluating and selecting the most effective embedding model for a specific domain from a vast number of options. In this study, we address this challenge by...

Full description

Saved in:
Bibliographic Details
Main Author: Changro Lee
Format: Article
Language:English
Published: Vilnius Gediminas Technical University 2025-04-01
Series:International Journal of Strategic Property Management
Subjects:
Online Access:https://ijspm.vgtu.lt/index.php/IJSPM/article/view/23637
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849715488472432640
author Changro Lee
author_facet Changro Lee
author_sort Changro Lee
collection DOAJ
description The recent proliferation of embedding models has enhanced the accessibility of textual data classification. However, the crucial challenge is evaluating and selecting the most effective embedding model for a specific domain from a vast number of options. In this study, we address this challenge by assessing the performance of embedding models based on their effectiveness in downstream tasks. We analyze consultation records maintained by an apartment management body in South Korea, and convert this textual data into numerical representations using various embedding models. The vectorized text is then categorized using a k-means clustering algorithm. The downstream task, specifically, the classification of consultation records, is evaluated using a quantitative metric (Silhouette score) and qualitative approaches (domain-specific knowledge and visual inspection). The qualitative approaches yield more reliable results than the quantitative approach. These findings are expected to be valuable for the various stakeholders in property management.
format Article
id doaj-art-3207f9fecc57449eb88d6dc3d0a13f73
institution DOAJ
issn 1648-715X
1648-9179
language English
publishDate 2025-04-01
publisher Vilnius Gediminas Technical University
record_format Article
series International Journal of Strategic Property Management
spelling doaj-art-3207f9fecc57449eb88d6dc3d0a13f732025-08-20T03:13:22ZengVilnius Gediminas Technical UniversityInternational Journal of Strategic Property Management1648-715X1648-91792025-04-0129210.3846/ijspm.2025.23637Evaluating embedding models for text classification in apartment managementChangro Lee0Department of Real Estate, Kangwon National University, 1 Kangwondaehak-gil, 24341 Chuncheon, Gangwon-do, Republic of Korea The recent proliferation of embedding models has enhanced the accessibility of textual data classification. However, the crucial challenge is evaluating and selecting the most effective embedding model for a specific domain from a vast number of options. In this study, we address this challenge by assessing the performance of embedding models based on their effectiveness in downstream tasks. We analyze consultation records maintained by an apartment management body in South Korea, and convert this textual data into numerical representations using various embedding models. The vectorized text is then categorized using a k-means clustering algorithm. The downstream task, specifically, the classification of consultation records, is evaluated using a quantitative metric (Silhouette score) and qualitative approaches (domain-specific knowledge and visual inspection). The qualitative approaches yield more reliable results than the quantitative approach. These findings are expected to be valuable for the various stakeholders in property management. https://ijspm.vgtu.lt/index.php/IJSPM/article/view/23637embedding modeltext dataclusteringdomain-specific knowledgeapartment management
spellingShingle Changro Lee
Evaluating embedding models for text classification in apartment management
International Journal of Strategic Property Management
embedding model
text data
clustering
domain-specific knowledge
apartment management
title Evaluating embedding models for text classification in apartment management
title_full Evaluating embedding models for text classification in apartment management
title_fullStr Evaluating embedding models for text classification in apartment management
title_full_unstemmed Evaluating embedding models for text classification in apartment management
title_short Evaluating embedding models for text classification in apartment management
title_sort evaluating embedding models for text classification in apartment management
topic embedding model
text data
clustering
domain-specific knowledge
apartment management
url https://ijspm.vgtu.lt/index.php/IJSPM/article/view/23637
work_keys_str_mv AT changrolee evaluatingembeddingmodelsfortextclassificationinapartmentmanagement