Wisdom of crowds and commodity pricing

We extract commodity-level sentiment from the Twittersphere in 2009-2020. A long-short strategy based on sentiment shifts more than doubles the Sharpe ratio of extant commodity factors. Commodities with lower (higher) sentiment shifts tend to be overvalued (undervalued) when the aggregate market is in backwardation (contango). The sentiment premium is more pronounced during periods of macro contraction and deteriorating funding liquidity. While the premium concentrates in commodities with higher tweet intensity, sentiment extracted from influential tweets (i.e., high number of retweets/likes) does not exhibit stronger predictive ability than low-attention tweets. Consistent with the overreaction hypothesis, the sentiment premium fully reverses 3 years postformation.