Emoticon Recommendation System to Richen Your Online Communication

Emoticon Recommendation System to Richen Your Online Communication

Yuki Urabe (Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan), Rafal Rzepka (Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan) and Kenji Araki (Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan)
DOI: 10.4018/ijmdem.2014010102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Japanese emoticons are widely used to express users' feelings and intentions in social media, blogs and instant messages. Japanese smartphone keypads have a feature that shows a list of emoticons, enabling users to insert emoticons simply by touching them. However, this list of emoticons contains more than 200, which is difficult to choose from, so a method to reorder the list and recommend appropriate emoticons to users is necessary. This paper proposes an emoticon recommendation method based on the emotive statements of users and their past selections of emoticons. The system is comprised of an affect analysis system and an original emoticon database: a table of 59 emoticons numerically categorized by 10 emotion types. The authors' experiments showed that 73.0% of chosen emoticons were among the top five recommended by the system, which is an improvement of 43.5% over the method used in current smartphones, which is based only on users' past emoticon selections.
Article Preview

Introduction

CMC (Computer-Mediated Communication) has become popular in recent years as it allows people to communicate regardless of time, limitations of physical distance, and familiarity (i.e. whether or not they know each other). However, in contrast to F2F (Face-to-Face) communication, text-based communication in CMC lacks the ability to convey nonverbal cues such as facial expression, attitude, and tone of voice (Jibril & Abdulah, 2013). These cues take up an estimated 93% of every day communication (Mehrabian, 1971) and enable humans to understand others’ feelings and intentions not only from the spoken words but also from their facial expressions showing emotion and attitudes (Fridlund, 1994). Therefore, we need to find a way to compensate for this lack of nonverbal cues in order to prevent confusion and express user intentions fully in CMC.

Emoticons, marks expressing faces or movement composed of letters and symbols, may serve as nonverbal surrogates in CMC (Walther & D’addario, 2001; Ptaszynski, 2012; Wei, 2012). Emoticons are used in CMC to express one’s feelings, enhance the sentence, and express humor (Derks, Bos & Grumbkow, 2008). Recipients can understand the sender’s intended emotions, attitudes, and attention clearly with emoticons in the sentence rather than by receiving only words in the sentence (Lo, 2008; Gajadhar & Green, 2005; Ip, 2002). Information conveyed by emoticons has a great importance in CMC which we should not ignore, and thus, research on emotion analysis from emoticons, and development of interfaces which support users expressing their feelings using emoticons are highly important.

Emoticons can be divided into two types: vertical style (e.g. “:) ”), mainly used in western countries and horizontal style (e.g. “(^_^)”), mainly used in Asian countries (Park, Barash, Fink & Cha, 2013). The vertical style emoticon is composed of symbols and English alphabet and is rotated by 90 degrees. Contrary to the vertical one, the horizontal style emoticon is un-rotated and easily comprehensible to a reader (Park et al., 2013). Moreover, the horizontal style is composed of symbols and many different kinds of characters from languages such as Japanese, Korean, Cyrillic, and so on (Robb, 2013; Pollack, 1996; Ashcraft, 2012). The number of emoticons in both styles differs greatly; that is, there are around 260 vertical style emoticons whereas horizontal style emoticons exceed 58,000 and are still increasing in recent years. These large numbers of emoticons are sophisticated enough to express nuances in meaning and may richen the quality of communication in CMC. However, it is difficult for users to find appropriate emoticons to express their intentions from these 58,000 emoticons.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing