A Comparative Study of Lexical and Semantic Emoji Suggestion Systems

Anonymous

Abstract: Emoji suggestion systems based on typed text have been proposed to encourage emoji usage and enrich text messaging; however, such systems’ actual effects on the chat experience remain unknown. We built an Android keyboard with both lexical (word-based) and semantic (meaning-based) emoji suggestion capabilities and compared these in two different studies. To investigate the effect of emoji suggestion in online conversations, we conducted a laboratory text-messaging study with 24 participants, and also a 15-day longitudinal field deployment with 18 participants. We found that lexical emoji suggestions increased emoji usage by 31.5% over a keyboard without suggestions, while semantic suggestions increased emoji usage by 125.1%. However, suggestion mechanisms did not affect the chatting experience significantly. From these studies, we formulate a set of design guidelines for future emoji suggestion systems that better support users’ needs.

TL;DR: We built an Android keyboard with both lexical (word-based) and semantic (meaning-based) emoji suggestion capabilities and compared their effects in two different chat studies.

Keywords: Emoji suggestion, text entry, text messaging, mobile chat