Salmon Stock Returns Around Market News

We examine the relationship between media news and trading behavior in the salmon market. For this, we create a share price index based on five salmon aquaculture companies trading on the Oslo Stock Exchange. We use the latent Dirichlet allocation algorithm to obtain news topics and a lexicon-based sentiment analysis. We find that topics relating to COVID-19 and sustainability have a significant negative impact on the salmon market, while topics on land-based aquaculture have a significant positive impact. The sentiment series based on the Loughran-McDonald lexicon is found to have a negative and insignificant effect on stock returns. Hence, we expand the lexicon with industry-specific words. A negative shock to sentiment within the news related to competitors foreshadows a significant increase in returns owing to the market’s competitive nature. Through our out-of-sample forecasting experiment, we find that the incorporation of news data can improve the predictive performance.