Detecting Sarcastic and Complimentary Exclamations in English with Intonation patterns and Acoustic Features: A Case Study

Sentiment analysis has been a significant topic in Natural Language Processing, human-computer interaction as well as emotion recognition technology. Exclamation, either complimentary or sarcastic, is a very typical sentence type to express strong emotions in everyday communication, social medias, customers' responses to products and services, cross-cultural communications as well as in security and forensics. Moreover, both types of exclamation can share the identical literal form but express distinctively opposite emotions or attitudes by means of linguistic contexts and intonation devices. However, there are very few studies on their subtle but unique speech features. To shed light on this demanding issue for sentiment analysis and human-computer reaction, the present study explores the two facets of exclamation in English in order to probe into the intonation patterns (tonality, tonicity and tone) and acoustic features (duration, pitch, and intensity) of sarcastic exclamation (SE) and complimentary exclamations (CE) in English. The findings reveal that both SE and CE share the similar tonality and tonicity patterns, but hugely differ in their tone patterns, and that they significantly distinguish from each other in three parameters of duration, two magnitudes of pitch and one scale of intensity.