Abstract-The emergence of big data analytics enables real time news analysis. Such analysis offers the possibility to instantly extract the sentiment conveyed by any newly published, textual information source. This paper investigates the existence of a causal relationship between news sentiment and stock prices. As such, we apply news sentiment analysis for unstructured, textual data to extract sentiment scores and utilize the Granger-causality test to determine the causal relationship between daily news sentiment scores and the corresponding stock market returns. Upon successfully identifying such a causal relationship with a time lag, we develop a real-time news sentiment index. This news sentiment index serves as a decision-support system in detecting a potential over-or undervaluation of stock prices given the news sentiment of available news sources. Thus, as a novelty, the news sentiment index serves as an early-warning system to detect irrational exuberance.