Inside 50,000 living rooms

an assessment of global residential ornamentation using transfer learning

Xi Liu, Clio Maria Andris, Zixuan Huang, Sohrab Rahimi

Research output: Contribution to journalArticle

Abstract

The global community decorates their homes based on personal decisions and contextual influences of their larger cultural and economic surroundings. The extent to which spatial patterns emerge in residential decoration practices has been traditionally difficult to ascertain due to the private nature of interior home spaces. Yet, measuring these patterns can reveal the presence of geographic culture hearths and/or globalization trends. In this work, we collected over one million geolocated images of interior living spaces from a popular home rental website, Airbnb (http://airbnb.com), and used transfer learning techniques to automatically detect the presence of key stylistic objects: plants, books, decor, wall art and predominance of vibrant colors. We investigated patterns of home decor practices for 107 cities on six continents, and performed a deep dive into six major U.S. cities. We found that world regions show statistically significant variation in decorative element prevalence, indicating differences in geographic cultural trends. At the U.S. neighborhood level, elements were only weakly spatially clustered and found to not correlate with socio-economic neighborhood variables such as income, unemployment rates, education attainment, residential property value, and racial diversity. These results may suggest that American residents in different socio-economic environments put similar effort into personalizing and caring for their homes. More broadly, our results represent a new view of worldwide human behavior and a new application of machine learning techniques to the exploration of cultural phenomena.

Original languageEnglish (US)
Article number4
JournalEPJ Data Science
Volume8
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Transfer Learning
Economics
Interior
Globalization
Unemployment
Human Behavior
Spatial Pattern
Correlate
Learning systems
Websites
Machine Learning
Education
Color
Trends

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Computer Science Applications
  • Computational Mathematics

Cite this

Liu, Xi ; Andris, Clio Maria ; Huang, Zixuan ; Rahimi, Sohrab. / Inside 50,000 living rooms : an assessment of global residential ornamentation using transfer learning. In: EPJ Data Science. 2019 ; Vol. 8, No. 1.
@article{23c5b588bba042caafe19a23a019162c,
title = "Inside 50,000 living rooms: an assessment of global residential ornamentation using transfer learning",
abstract = "The global community decorates their homes based on personal decisions and contextual influences of their larger cultural and economic surroundings. The extent to which spatial patterns emerge in residential decoration practices has been traditionally difficult to ascertain due to the private nature of interior home spaces. Yet, measuring these patterns can reveal the presence of geographic culture hearths and/or globalization trends. In this work, we collected over one million geolocated images of interior living spaces from a popular home rental website, Airbnb (http://airbnb.com), and used transfer learning techniques to automatically detect the presence of key stylistic objects: plants, books, decor, wall art and predominance of vibrant colors. We investigated patterns of home decor practices for 107 cities on six continents, and performed a deep dive into six major U.S. cities. We found that world regions show statistically significant variation in decorative element prevalence, indicating differences in geographic cultural trends. At the U.S. neighborhood level, elements were only weakly spatially clustered and found to not correlate with socio-economic neighborhood variables such as income, unemployment rates, education attainment, residential property value, and racial diversity. These results may suggest that American residents in different socio-economic environments put similar effort into personalizing and caring for their homes. More broadly, our results represent a new view of worldwide human behavior and a new application of machine learning techniques to the exploration of cultural phenomena.",
author = "Xi Liu and Andris, {Clio Maria} and Zixuan Huang and Sohrab Rahimi",
year = "2019",
month = "12",
day = "1",
doi = "10.1140/epjds/s13688-019-0182-z",
language = "English (US)",
volume = "8",
journal = "EPJ Data Science",
issn = "2193-1127",
publisher = "Springer Science + Business Media",
number = "1",

}

Inside 50,000 living rooms : an assessment of global residential ornamentation using transfer learning. / Liu, Xi; Andris, Clio Maria; Huang, Zixuan; Rahimi, Sohrab.

In: EPJ Data Science, Vol. 8, No. 1, 4, 01.12.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Inside 50,000 living rooms

T2 - an assessment of global residential ornamentation using transfer learning

AU - Liu, Xi

AU - Andris, Clio Maria

AU - Huang, Zixuan

AU - Rahimi, Sohrab

PY - 2019/12/1

Y1 - 2019/12/1

N2 - The global community decorates their homes based on personal decisions and contextual influences of their larger cultural and economic surroundings. The extent to which spatial patterns emerge in residential decoration practices has been traditionally difficult to ascertain due to the private nature of interior home spaces. Yet, measuring these patterns can reveal the presence of geographic culture hearths and/or globalization trends. In this work, we collected over one million geolocated images of interior living spaces from a popular home rental website, Airbnb (http://airbnb.com), and used transfer learning techniques to automatically detect the presence of key stylistic objects: plants, books, decor, wall art and predominance of vibrant colors. We investigated patterns of home decor practices for 107 cities on six continents, and performed a deep dive into six major U.S. cities. We found that world regions show statistically significant variation in decorative element prevalence, indicating differences in geographic cultural trends. At the U.S. neighborhood level, elements were only weakly spatially clustered and found to not correlate with socio-economic neighborhood variables such as income, unemployment rates, education attainment, residential property value, and racial diversity. These results may suggest that American residents in different socio-economic environments put similar effort into personalizing and caring for their homes. More broadly, our results represent a new view of worldwide human behavior and a new application of machine learning techniques to the exploration of cultural phenomena.

AB - The global community decorates their homes based on personal decisions and contextual influences of their larger cultural and economic surroundings. The extent to which spatial patterns emerge in residential decoration practices has been traditionally difficult to ascertain due to the private nature of interior home spaces. Yet, measuring these patterns can reveal the presence of geographic culture hearths and/or globalization trends. In this work, we collected over one million geolocated images of interior living spaces from a popular home rental website, Airbnb (http://airbnb.com), and used transfer learning techniques to automatically detect the presence of key stylistic objects: plants, books, decor, wall art and predominance of vibrant colors. We investigated patterns of home decor practices for 107 cities on six continents, and performed a deep dive into six major U.S. cities. We found that world regions show statistically significant variation in decorative element prevalence, indicating differences in geographic cultural trends. At the U.S. neighborhood level, elements were only weakly spatially clustered and found to not correlate with socio-economic neighborhood variables such as income, unemployment rates, education attainment, residential property value, and racial diversity. These results may suggest that American residents in different socio-economic environments put similar effort into personalizing and caring for their homes. More broadly, our results represent a new view of worldwide human behavior and a new application of machine learning techniques to the exploration of cultural phenomena.

UR - http://www.scopus.com/inward/record.url?scp=85061713419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061713419&partnerID=8YFLogxK

U2 - 10.1140/epjds/s13688-019-0182-z

DO - 10.1140/epjds/s13688-019-0182-z

M3 - Article

VL - 8

JO - EPJ Data Science

JF - EPJ Data Science

SN - 2193-1127

IS - 1

M1 - 4

ER -