Twitter Sentiments and Commodity Markets: A Dynamic Multifractal Detrended Cross‐Correlation Analysis

Twitter has become one of the most widely used social networking sites, with millions of users worldwide, and it provides daily indicators of consumers' perceptions of inflation. Hence, to investigate the cross‐correlation between Twitter sentiment and commodity markets, we employed the daily S&P 500 Twitter Sentiment Index (SPSNTUP) and four diverse and well‐known commodity indices, namely Commodity Research Bureau Index (CRBI), Baltic Dry Index (BDI), London Metal Index (LME), and Brent oil prices (BROIL). Multifractal detrended cross correlation analysis (MF‐DCCA) was applied in a multifractal context, using daily data from February 6, 2018, to December 12, 2022. The key findings are as follows: (i) all the commodity‐specific pairs with SPSNTUP exhibit significant multifractal properties; (ii) the evidence of power‐law cross‐correlation suggests that significant changes in SPSNTUP are likely to be followed by larger price changes in commodity markets pairs, namely SPSNTUP‐CRBI SPSNTUP‐BDI, SPSNTUP‐BROIL and SPSNTUP‐LME; (iii) SPSNTUP‐BROIL exhibits the highest multifractal patterns, while SPSNTUP‐LME reports the lowest multifractal trend; (iv) commodity markets demonstrate more persistent cross‐correlations for small fluctuations than for large fluctuations. Lastly, these results provide valuable propositions for policymakers and commodity market participants.