Title :
Relationship between Emotional Words and Emoticons in Tweets
Author :
Soranaka, K. ; Matsushita, M.
Author_Institution :
Kansai Univ., Suita, Japan
Abstract :
Asynchronous communication using text messaging is a major mode of o n l i n e 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 expression using icons for facial expressions, are often used to supplement or adjust the verbal part of t h e text, though 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 t h e emotions in the s e n d e r ´ 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 c a n change between positive and negative emotion according to the co-occurring words.
Keywords :
electronic messaging; emotion recognition; social networking (online); text analysis; asynchronous communication; cooccurring words; emoticons; emotion estimation; emotional words; facial expression; fluent communication; negative emotion; online communication; positive emotion; recipient perception; sender intended tone; text messaging; textual expression; tweets; Context; Databases; Dictionaries; Educational institutions; Electric shock; Strain; Twitter; Twitter; emoticon; emotional words; text mining;
Conference_Titel :
Technologies and Applications of Artificial Intelligence (TAAI), 2012 Conference on
Conference_Location :
Tainan
Print_ISBN :
978-1-4673-4976-5
DOI :
10.1109/TAAI.2012.30