Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
Does news tone help forecast oil? In this paper, we study the relationship between news tone and crude oil prices and evaluate the role news tone plays in the ability to forecast oil prices. Specifically, we use a recently developed oil-specific dictionary as well as a widely used general financial dictionary, to directly measure the sentiment of 3579 oil news articles from Financial Times for actual oil price forecasting. We find compelling evidence that news tone constructed by the oil dictionary helps forecast monthly oil prices out-of-sample over short horizons, while the news tone constructed by financial dictionary shows no out-of-sample forecasting power at all. We verify and document the economic significance of the best performing forecasting model against the others and a naive buy-hold strategy. We argue that the forecasting power of news tone is data and method dependent, and we underscore the correct use of domain-specific dictionaries in financial sentiment analysis.