Computing Consumer Sentiment in Germany via Social Media Data
Publikation: Arbeits- oder Diskussionspapiere und Berichte › Arbeits- oder Diskussionspapiere
Standard
Computing Consumer Sentiment in Germany via Social Media Data. / Karaman Örsal, Deniz; Sturm, Silke.
Hamburg : Universität Hamburg, 2021. (Hamburg Discussion Papers in International Economics; Nr. 7).Publikation: Arbeits- oder Diskussionspapiere und Berichte › Arbeits- oder Diskussionspapiere
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - UNPB
T1 - Computing Consumer Sentiment in Germany via Social Media Data
AU - Karaman Örsal, Deniz
AU - Sturm, Silke
PY - 2021
Y1 - 2021
N2 - Survey-based consumer confidence indicators are mostly reported with adelay and are a result of time consuming and expensive consumer surveys.In this study, to measure the current consumer confidence in Germany, wedevelop an approach, in which we compute the consumer sentiment usingpublic Tweets from Germany. To achieve this goal we develop a new sentimentscore. To measure the consumer sentiment, we use text-mining tools and publicTweets from May 2019 to August 2020. Our findings indicate that there is ahigh correlation between the consumer confidence indicator based on surveydata, and the consumer sentiment that we compute using data from Twitterplatform. With our approach, we are even able to forecast the change in nextmonth’s consumer confidence.
AB - Survey-based consumer confidence indicators are mostly reported with adelay and are a result of time consuming and expensive consumer surveys.In this study, to measure the current consumer confidence in Germany, wedevelop an approach, in which we compute the consumer sentiment usingpublic Tweets from Germany. To achieve this goal we develop a new sentimentscore. To measure the consumer sentiment, we use text-mining tools and publicTweets from May 2019 to August 2020. Our findings indicate that there is ahigh correlation between the consumer confidence indicator based on surveydata, and the consumer sentiment that we compute using data from Twitterplatform. With our approach, we are even able to forecast the change in nextmonth’s consumer confidence.
KW - Economics
KW - consumer sentiment
KW - consumer confidence
KW - twitter
KW - sentiment analysis
UR - https://www.econstor.eu/bitstream/10419/229183/1/hdpie-no07.pdf
M3 - Working papers
T3 - Hamburg Discussion Papers in International Economics
BT - Computing Consumer Sentiment in Germany via Social Media Data
PB - Universität Hamburg
CY - Hamburg
ER -