表情符号
计算机科学
感知
自然语言处理
人工智能
情绪分析
心理学
万维网
社会化媒体
神经科学
作者
Jose Berengueres,Dani Castro
标识
DOI:10.1109/bigdata.2017.8258461
摘要
Previous research has traditionally analyzed emoji sentiment from the point of view of the reader of the content not the author. Here, we analyze emoji sentiment from the point of view of the author and present an emoji sentiment benchmark that was built from an employee happiness dataset where emoji happen to be annotated with daily happiness of the author of the comment. The data spans over 3 years, and 4k employees of 56 companies based in Barcelona. We compare sentiment of writers to readers. Results indicate that, there is an 82% agreement in how emoji sentiment is perceived by readers and writers. The disagreement concentrates in negative emoji, where the authors report to feel 26% worse than perceived by readers. Emoji use was not found to be correlated with author moodiness. Authors that use emoji are happier than authors that never use emoji.
科研通智能强力驱动
Strongly Powered by AbleSci AI