Dynamic impacts of online investor sentiment on international crude oil prices

In recent years, international crude oil prices have been subject to unusually high fluctuations due to the ravages of the COVID-19 epidemic. Under such extreme market conditions, online investor sentiment can strengthen the correlation between oil price changes and external events. We use a (rolling-window) structural vector autoregression method to investigate the dynamic impact of online investor sentiment on WTI crude oil prices before and after the COVID-19 pandemic across multiple topics of price, supply, demand, and so on, which aims to explore the fluctuation mechanism driven by sentiment and the price changes triggered by public health events. The proposed aspect-level sentiment analysis approach can effectively distinguish and measure sentiment scores of different aspects of the oil market. Our results show that the constructed oil price prosperity index contributes 49.84% to the long-term fluctuations of WTI oil price, ranking first among the influencing factors considered. In addition, the peak value of impulse shocks to WTI oil prices rose from 6.47% to 8.40% during the period of dramatic price volatility caused by the epidemic. The results sketch the mechanisms by which investor sentiment can affect crude oil prices, which help policymakers and investors protect against extreme risks in the oil market.

Automated summary

In recent years, international crude oil prices have experienced significant fluctuations due to the impact of the COVID-19 epidemic. Online investor sentiment can strengthen the correlation between oil price changes and external events in such extreme market conditions. Using a rolling-window structural vector autoregression method, this study investigates the dynamic impact of online investor sentiment on WTI crude oil prices before and after the pandemic, covering various aspects of price, supply, demand, etc., aiming to explore the fluctuation mechanism driven by sentiment and the price changes caused by public health events. The proposed aspect-level sentiment analysis approach effectively distinguishes and measures sentiment scores of different aspects of the oil market. The findings provide insights into the mechanisms through which investor sentiment influences crude oil prices, assisting policymakers and investors in mitigating extreme risks in the oil market.