Opinion mining in management research: the state of the art and the way forward

In the past decade, the explosive growth of social media has led to the emergence of a wide variety of information sources that can significantly impact individual level decision making processes. This has resulted in an increasing availability of unstructured textual data and automated evaluation of opinions, attitudes, and emotions has been accepted as an indispensable analytical tool in diverse domains. Consequently, there is a strong need to understand the underlying technical aspects of this emerging new field of analysis. In the current paper we address this need by reviewing the state of the art in sentiment analysis, summarize some of the important recent applications of sentiment analysis and offer future directions for further research. This paper differs from earlier reviews in a number of ways: first, it offers preliminary technical exposition of various techniques following a simple classification scheme so as to help potential future users to develop overall understanding of this rapidly developing field; second, it discusses in greater detail some of the more recently proposed techniques to solve a set of problems in specific management domains; third, it also presents some examples to elucidate how combining sentiment analysis techniques with conventional econometric approaches can help us solve business specific problems. The main goal of this paper is to generate more interest about this interesting new domain among management researchers.