EmojiNet: Building a Machine Readable Sense Inventory for Emoji

TitleEmojiNet: Building a Machine Readable Sense Inventory for Emoji
Publication TypeConference Proceedings
Year of Publication2016
AuthorsSanjaya Wijeratne, Lakshika Balasuriya, Amit Sheth, Derek Doran
EditorEmma Spiro, Yong-Yeol Ahn
Conference Name8th International Conference on Social Informatics (SocInfo 2016)
Volume10046
Pagination527-541
Date Published12/2016
PublisherSpringer International Publishing
Conference LocationBellevue, WA
ISBN Number978-3-319-47880-7
KeywordsEmoji Analysis, Emoji Sense Disambiguation, EmojiNet
Abstract

Emoji are a contemporary and extremely popular way to enhance electronic communication. Without rigid semantics attached to them, emoji symbols take on different meanings based on the context of a message. Thus, like the word sense disambiguation task in natural language processing, machines also need to disambiguate the meaning or ‘sense’ of an emoji. In a first step toward achieving this goal, this paper presents EmojiNet, the first machine readable sense inventory for emoji. EmojiNet is a resource enabling systems to link emoji with their context-specific meaning. It is automatically constructed by integrating multiple emoji resources with BabelNet, which is the most comprehensive multilingual sense inventory available to date. The paper discusses its construction, evaluates the automatic resource creation process, and presents a use case where EmojiNet disambiguates emoji usage in tweets. EmojiNet is available online for use at http://emojinet.knoesis.org.

DOI10.1007/978-3-319-47880-7_33
Additional Information

In the reviewers’ words:

    "Emoji is an important tool of nonverbal communication, but its usage lacks 'universal', uniform and rigorous semantic attachments. This paper introduces the first machine readable sense inventory for emoji—EmojiNet, a resource enabling systems to link emoji with its context-specific meaning. It is automatically constructed by integrating multiple emoji resources. It is a useful application tool for public use in online communication that will facilitate human interaction.”

    "The representation of emojis with a tuple of 8 field is well designed and puts in a single place almost all the information available about emojis in previous dictionaries, reported in the previous work section. The authors evaluate the resource under the aspects of image detection/alignment and word sense disambiguation. both evaluation tasks are performed correctly."