The relationship analysis between media articles and the apartment transaction price index using BERTopic
Yeon Dong Lee1 · Kyung Kyu Seo2 · Young Seuk Cho3
13Department of Statistics, Pusan University
2Department of Real Estate, Catholic University of Daegu
2Department of Real Estate, Catholic University of Daegu
Correspondence to: 1 Ph.D. candidate, Department of Statistics, Pusan University, Busan 46241, Korea.
2 Professor, Department of Real Estate, Catholic University of Daegu, Daegu 38430, Korea.
3 Corresponding author: Professor, Department of Statistics, Pusan University, Busan 46241, Korea. E-mail: choys@pusan.ac.kr
2 Professor, Department of Real Estate, Catholic University of Daegu, Daegu 38430, Korea.
3 Corresponding author: Professor, Department of Statistics, Pusan University, Busan 46241, Korea. E-mail: choys@pusan.ac.kr
Received October 28, 2024; Revised November 18, 2024; Accepted November 20, 2024.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
- Abstract
- This study aims to propose a novel research method that utilizes BERTopic, a natural language processing technique, to analyze the relationship between news articles and apartment transaction price indices. The dataset consists of 647,313 real estate-related news article titles collected over a period of 11 years, from 2012 to 2022. Additionally, the study incorporates apartment transaction price index data provided by the Korea Real Estate Board for the same period. Topics were extracted using BERTopic, and the key terms constituting each topic were identified. To assess the correlation between the monthly distribution of topic terms and the apartment transaction price indices, the Kullback-Leibler divergence was calculated. This method enabled the identification of how specific topic terms were associated with the apartment transaction price indices of major cities. The analysis revealed a significant correlation between specific topic terms and the apartment transaction price indices. Notably, certain topic terms exhibited a stronger association with the apartment transaction price indices than with the monthly article frequency.
- Keywords : Apartment transaction price index, BERTopic, KL-divergence, media articles, real estate market
Full Text(PDF) Free
