Textual variations affect human judgements of sentiment values

Electronic word-of-mouth communication in the form of online reviews influences people's product or service choices. People use text features to add or emphasise feelings and emotions in their text. The text emphasis can come in as capital letters, letter repetition, exclamation marks and emoticons. The existing literature has not paid sufficient attention to the effects of such textual variations on human text interpretation. This paper presents an analysis of text variations that can affect the interpretation of a text. A total of 1,041 online comments were collected, in which seven types of the most used textual variations were identified and simulated for hypothesis testing. Sentiment scores from 500 participants were collected to rate the value expressed for each of the textual variations. Statistical analysis showed that collected ratings are significant for the accurate calculation of sentiment values for short comments. Furthermore, the performance of ten existing sentiment tools was analysed based on seven textual variations. Results indicate that those tools should consider these textual variations to fully reflect a human interpretation on the text variations.