Abstract

As the use of automated social media analysis tools surges, concerns over accuracy of analytics have increased. Some tentative evidence suggests that sarcasm alone could account for as much as a 50% drop in accuracy when automatically detecting sentiment. This paper assesses and outlines the prevalence of sarcastic and ironic language within social media posts. Several past studies proposed models for automatic sarcasm and irony detection for sentiment analysis; however, these approaches result in models trained on training data of highly questionable quality, with little qualitative appreciation of the underlying data. To understand the issues and scale of the problem, we are the first to conduct and present results of a focused manual semantic annotation analysis of two datasets of Twitter messages, associated with; hashtags commonly employed in automated sarcasm and irony detection approaches, and tweets relating to 25 distinct events, including, scandals, product releases, cultural events, accidents, terror incidents, etc. We also highlight the contextualised use of multi-word hashtags in the communication of humour, sarcasm and irony, pointing out that many sentiment analysis tools simply fail to recognise such hashtag-based expressions. Our findings also offer indicative evidence regarding the quality of training data used for automated machine learning models in sarcasm, irony and sentiment detection. Worryingly only 15% of tweets labelled as sarcastic were truly sarcastic. We highlight the need for future research studies to rethink their approach to data preparation and a more careful interpretation of sentiment analysis.