Empirical Evaluation of Automated Sentiment Analysis as a Decision Aid

Research has consistently shown that online word-of-mouth (WOM) plays an important role in shaping customer attitudes and behaviors. Yet, despite their documented utility, explicit user scores, such as star ratings have limitations in certain contexts. Automatic sentiment analysis (SA), an analytics technique that assesses the “tone” of text, has been proposed as a way to deal with these shortcomings. While extant research on SA has focused on issues surrounding the design of algorithms and output accuracy, this research-in-progress examines the behavioral and interface design issues in regards to SA scores as perceived by their intended users. Specifically, in an online context, we experimentally investigate the role of product (product category) and review characteristics (review extremity) in influencing the perceived usefulness of SA scores. Further, we investigate whether variations in how the SA scores are presented to the user, and the nature of the scores themselves further affect user perceptions.