From Corporate Disclosure to Social Media – Understanding Real Estate Markets with Textual Analysis - University of Regensburg Publication Server

Item type:	Thesis of the University of Regensburg (PhD)
Open Access Type:	Primary Publication
Volume:	105
Date:	31 August 2023
Referee:	Prof. Dr. Wolfgang Schäfers and Prof. Dr. Bertram Steininger
Date of exam:	19 July 2023
Institutions:	Business, Economics and Information Systems > Institut für Immobilienenwirtschaft / IRE\|BS > Lehrstuhl für Immobilienmanagement (Prof. Dr. Wolfgang Schäfers)
Keywords:	Real Estate Markets; Natural Language Processing; Textual Analysis; Sentiment; Topic Modelling
Dewey Decimal Classification:	300 Social sciences > 330 Economics
Status:	Published
Refereed:	Yes, this version has been refereed
Created at the University of Regensburg:	Yes
Item ID:	54637

Abstract (English)

In the dissertation, Natural Language Processing techniques are applied to analyze indicators such as investor sentiment, informativeness, and reporting intensity in real estate-related texts and to show their relation to real estate markets. It becomes clear that corporate publications, newspapers, and social media provide valuable information for investors and enable inferences about market ...

Abstract (English)

In the dissertation, Natural Language Processing techniques are applied to analyze indicators such as investor sentiment, informativeness, and reporting intensity in real estate-related texts and to show their relation to real estate markets. It becomes clear that corporate publications, newspapers, and social media provide valuable information for investors and enable inferences about market developments. It also shows that the forecasting quality can be significantly increased with more advanced methods.

Translation of the abstract (German)

In der Dissertation werden Techniken des Natural Language Processings angewendet um Indikatoren wie die Investorenstimmung, Informativität und Berichterstattungsintensität in immobilienbezogenen Texten zu analysieren und deren Zusammenhang mit Immobilienmärkten aufzuzeigen. Es wird deutlich, dass Unternehmenspublikationen, Fachzeitschriften und Soziale Medien wertvolle Informationen für Anleger ...

Translation of the abstract (German)

In der Dissertation werden Techniken des Natural Language Processings angewendet um Indikatoren wie die Investorenstimmung, Informativität und Berichterstattungsintensität in immobilienbezogenen Texten zu analysieren und deren Zusammenhang mit Immobilienmärkten aufzuzeigen. Es wird deutlich, dass Unternehmenspublikationen, Fachzeitschriften und Soziale Medien wertvolle Informationen für Anleger bereitstellen und Rückschlüsse auf Marktentwicklungen ermöglichen. Dabei zeigt sich auch, dass die Prognosequalität mit fortschrittlicheren Methoden deutlich gesteigert werden kann.

From Corporate Disclosure to Social Media – Understanding Real Estate Markets with Textual Analysis

Details

Preview

Export bibliographical data

Abstract (English)

Abstract (English)

Translation of the abstract (German)

Translation of the abstract (German)

Download Statistics

Downloads

More literature (via CORE)

University Library