Abstract
Asynchronous communication using text messaging is a major mode of online communication. It is simple and easy to use; however, there is often an inconsistency between the sender's intended tone and how the recipient perceives it. Emoticons, additional textual expressions that use icons to represent facial expressions, are often used to supplement or adjust the verbal part of the text; however, the problem persists. The goal of our research is to solve the problem by developing a system that supports fluent communication. The system would estimate the emotions in the sender's text and note whether different intentions may be conveyed. For that purpose, we analyzed concurrences between emotional words and emoticons in a text. We observed the following: (1) There are cases when the emotion represented in words and the emotion represented by the emoticon are inconsistent, (2) The expressed emotion can change between positive and negative emotions according to the co-occurring words.
Information
Book title
International Conference on Technologies and Applications of Artificial Intelligence
Pages
262-265
Date of issue
2012/11/16
Date of presentation
2012/11/17
Location
Tainan, Taiwan
DOI
10.1109/TAAI.2012.30
Citation
Kaito Soranaka, Mitsunori Matsushita. Relationship Between Emotional Words and Emoticons in Tweets, International Conference on Technologies and Applications of Artificial Intelligence , pp.262-265, 2012.