TY - JOUR
T1 - Applied sentiment analysis on a real estate advertisement recommendation model
AU - Lin, Regina Fang Ying
AU - Wu, Jiesheng
AU - Tseng, Kuo Kun
AU - Tang, Yuk Ming
AU - Liu, Lu
N1 - Funding Information:
We thank Shenzhen Government for generously providing the funding for this research [JCYJ20190806144609107, HA11409015, and 20,200,829,144,221,001]. We also thank the anonymous referees for their comments and guidance. All errors are ours.
Publisher Copyright:
© 2022 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2022/2/27
Y1 - 2022/2/27
N2 - Recently, the data generated are exploding in the information age. In the post-COVID-19 era, some real estate contracts have been signed online, and online advertisement recommendation has become a new way to reduce the searching cost. Therefore, the model in which real estate online recommendations can be made suitable without user preferences has become a tricky problem. This study uses sentiment and economic data to predict real estate sales and then made an advertisement recommendation from the forecast results. The 2SA-RERec (Two Sentiment Analysis of Real Estate Recommendation) model is proposed, which shows the highest accuracy among the others.
AB - Recently, the data generated are exploding in the information age. In the post-COVID-19 era, some real estate contracts have been signed online, and online advertisement recommendation has become a new way to reduce the searching cost. Therefore, the model in which real estate online recommendations can be made suitable without user preferences has become a tricky problem. This study uses sentiment and economic data to predict real estate sales and then made an advertisement recommendation from the forecast results. The 2SA-RERec (Two Sentiment Analysis of Real Estate Recommendation) model is proposed, which shows the highest accuracy among the others.
KW - back-propagation neural network
KW - grey system theory
KW - Real estate online advertisement recommendation model
KW - seasonal and trend decomposition using loess
KW - sentiment analysis
UR - http://www.scopus.com/inward/record.url?scp=85125948476&partnerID=8YFLogxK
U2 - 10.1080/17517575.2022.2037158
DO - 10.1080/17517575.2022.2037158
M3 - Journal article
AN - SCOPUS:85125948476
SN - 1751-7575
JO - Enterprise Information Systems
JF - Enterprise Information Systems
ER -