The role of tweets in agricultural export

An approach from text-mining and time-series analyses

Bibliographic Data

ID21295146
AuthorsYutaro Inoue (0009-0009-6113-7557, The University of Tokyo), Shinsaku Nakajima (0000-0002-1376-9033, Meiji University)
Year2024
Volume126
Issue4
Pages1597-1616
Publication date2024-03-15
Open AccessYes
TypeARTICLE
VenueBritish Food Journal (JOURNAL)
Journal identifiersISSN: 0007-070X • E-ISSN: 1758-4108
PublisherEmerald (PUBLISHER)
DOI10.1108/bfj-07-2023-0623
OpenAlexW4390764133
LanguageEN
References cited32

Purpose This study aims to investigate the relationship between consumer awareness of Zespri International Limited (ZespriTM) and its sales promotion in Japan and the recent expansion of New Zealand (NZ) kiwifruit imported into Japan. Design/methodology/approach Tweets mentioning ZespriTM were utilised as a proxy of such awareness. They were first summarised using two text-mining techniques: tf-idf scoring and a co-occurrence network graph. Afterwards, the authors estimated a tri-variate vector autoregression (VAR) model consisting of the net imports of NZ kiwifruit in Japan, unit import price and number of tweets. Additionally, the occurrence frequency of tweets with “Kiwi Brothers”, promotional characters for ZespriTM’s sales, was added to the model, and a tetra-variate VAR model was estimated. Finally, Granger-causality tests, an estimation of the impulse response function and forecast error variance decomposition was conducted. Findings All these variables were found to Granger-cause each other. Furthermore, a shock in the document frequency of “Kiwi Brothers” significantly affected Japan’s kiwifruit imports from NZ, explaining approximately 20% of future imports. ZespriTM’s distinctive sales promotion was, thus, found to contribute in part to the recent increase in NZ’s kiwifruit export to Japan. Originality/value This paper is the first to apply text-regression methodology to food consumption research; it contributes to food consumption research by proposing a practical way to combine tweets with outcome variables using a time-series analysis

Advertising · Business · Econometrics · Economics · Granger causality · Political science · Promotion (chess) · Proxy (statistics) · Statistics · Time series · Variance decomposition of forecast errors · Vector autoregression · Digital Marketing and Social Media · Mathematics · Wine Industry and Tourism

Tools

Open DOI