An Analysis of the Impact of Fukushima Daiichi Nuclear Power Plant Accident on Seafood Consumption Using Sentiment Analysis: A Case Study on Mackerel

This study explores how negative information about seafood impacts seafood consumption by extrapolating the lagged effect that the media coverage on Fukushima Daiichi nuclear power plant accident has on the domestic mackerel consumption. This paper collected news articles from January 2013 to December 2021 and derived a monthly sentiment index by using a Long Short-Term Memory (LSTM) sentiment analysis model. In the empirical analysis, Polynomial Distributed Lag (PDL) Model was employed to estimate the lagged effects of sentiment index, domestic mackerel production, Norwegian mackerel imports, and domestic fresh and chilled mackerel prices on domestic mackerel consumption. In addition, impulse response analysis was applied to investigate the relationship between Norwegian import volume and sentiment index variable. The empirical findings showed that the media coverage, up to four months prior to the present moment, reduced the current consumption by 1.2%, while the shocks to the sentiment index increased the Norwegian mackerel imports by 0.7% to 30.8%, two to six months after the shocks.