Emoticon Analysis for Chinese Social Media and E-commerce

Abstract

This article presents a novel system, AZEmo, which extracts and classifies emoticons from the ever-growing critical Chinese social media and E-commerce. An emoticon is a meta-communicative pictorial representation of facial expressions, which helps to describe the sender’s emotional state. To complement non-verbal communication, emoticons are frequently used in social media websites. However, limited research has been done to effectively analyze the affects of emoticons in a Chinese context. In this study, we developed an emoticon analysis system to extract emoticons from Chinese text and classify them into one of seven affect categories. The system is based on a kinesics model that divides emoticons into semantic areas (eyes, mouths, etc.), with improvements for adaptation in the Chinese context. Machine-learning methods were developed based on feature vector extraction of emoticons. Empirical tests were conducted to evaluate the effectiveness of the proposed system in extracting and classifying emoticons, based on corpora from a video sharing website and an E-commerce website. Results showed the effectiveness of the system in detecting and extracting emoticons from text and in interpreting the affects conveyed by emoticons.