This paper presents the release of EmojiNet, the largest machine-readable emoji sense inventory that links Unicode emoji representations to their English meanings extracted from the Web. EmojiNet is a dataset consisting of: (i) 12,904 sense labels over 2,389 emoji, which were extracted from the web and linked to machine-readable sense definitions seen in BabelNet; (ii) context words associated with each emoji sense, which are inferred through word embedding models trained over Google News corpus and a Twitter message corpus for each emoji sense definition; and (iii) recognizing discrepancies in the presentation of emoji on different platforms, specification of the most likely platform-based emoji sense for a selected set of emoji. The dataset is hosted as an open service with a REST API and is available at http://emojinet.knoesis.org/. The development of this dataset, evaluation of its quality, and its applications including emoji sense disambiguation and emoji sense similarity are discussed.
Link to paper - http://knoesis.org/sites/default/files/ICWSM_2017_EmojiNet_Final_Wijeratne.pdf
EmojiNet: An Open Service and API for Emoji Sense Discovery
1. EmojiNet: An Open Service and API for
Emoji Sense Discovery
Ohio Center of Excellence in Knowledge-enabled Computing (Kno.e.sis)
Wright State University, Dayton, OH, USA
Presented at the 11th International AAAI Conference on Web and Social Media (ICWSM 2017)
Montreal, Canada, 15th – 18th May, 2017
Lakshika Balasuriya
lakshika@knoesis.org
Sanjaya Wijeratne
sanjaya@knoesis.org
Derek Doran
derek@knoesis.org
Amit Sheth
amit@knoesis.org
2. 2Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
What does this emoji mean
3. 3Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
What does this emoji mean
Source – https://youtu.be/5JdVsbNqYno
4. 4Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
What does this emoji mean
Source – https://youtu.be/5JdVsbNqYno
5. 5Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
What does this emoji mean
U+1F481 INFORMATION DESK PERSON
6. 6Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
What does this emoji mean
7. 7Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
What does this emoji mean
Source – https://youtu.be/5JdVsbNqYno
8. 8Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
What does this emoji mean
Source – https://media.giphy.com/media/BNKGM6uOgPhp6/giphy.gif
9. 9Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
What does this emoji mean
U+1F450 OPEN HANDS SIGN
10. 10
What is EmojiNet
A dataset of emoji meanings and interpretations
Almost 13,000 senses: a word(pos_tag)pair
conveying notional interpretations of an emoji and
the part of speech tag of the interpretations
Includes many possible senses per emoji
Agglomerates data across open web resources, connects
sense labels to sense definitions by WSD task supported by
embedding models to BabelNet
Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
11. 11
Emoji is ambiguous – often, emoji are filtered, or
otherwise not considered in NLP tasks on CMC
EmojiNet offers a source of emoji meanings and
context towards emoji disambiguation
Goal: Support NLP, social media, CMC work trying
to extract meaning from emoji-laden (short) text
Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
Why EmojiNet
Source – https://goo.gl/rjS1hX
13. 13
EmojiNet Sense Queries
Emoji Sense Distribution
Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
14. 14
EmojiNet Sense Queries
Emoji Sense Distribution
Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
icing(noun)
pudding(noun)
stink(verb)
crappy(adjective)
15. 15
EmojiNet Sense Queries
Emoji Sense Distribution
Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
cutie(noun)
infatuation(noun)
hug(verb)
flirty(adjective)
16. 16
EmojiNet Sense Queries
Emoji Sense Distribution
Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
fashion(noun)
girl(noun)
wearing(verb)
female(adjective)
17. 17Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
Example Application –
Emoji Similarity
Emoji Similarity – Similar Emoji Form Clusters
Emoji Pair Similarity
0.60
0.57
0.56
0.52
0.52
0.50
0.50
0.50
0.48
0.47
Jaccard Similarity of Emoji Based on
Emoji Sense Labels
18. 18Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
EmojiNet Dataset and REST API
The dataset is available for use/download in
many formats
Browse the Dataset – http://emojinet.knoesis.org/
Download as flat files, Platform-specific emoji
meanings, Emoji Similarity Datasets available at –
http://emojinet.knoesis.org/datasets.php
Programmatically Access EmojiNet via a REST API,
Documentation, Sample API Requests and JSON
Responses available at –
http://emojinet.knoesis.org/api.php
19. 19Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
Applications of EmojiNet – Emoji Sense
Disambiguation
We selected 25 most commonly misunderstood
emoji and selected 50 tweets for each emoji
Used Simplified LESK algorithm for disambiguation
Context words were learned for each emoji sense
definition using Twitter and Google News-based word
embedding models
Twitter-based embeddings outperform others
Top 10 Emoji based on the Emoji Sense Disambiguation Accuracy (in % values)
20. 20SML @ IJCAI 2016 Wijeratne, Sanjaya et al. Word Embeddings to Enhance Twitter Gang Member Profile Identificationderek@knoesis.org http://knoesis.org/people/derek/
Thank You!
Visit us at http://emojinet.knoesis.org/
21. 21Wijeratne, Sanjaya et al. EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017.
Acknowledgement
We are grateful to Nicole Selken, the designer of The Emoji Dictionary and Jeremy
Burge, the founder of Emojipedia for giving us the permission to use their web
resources for our research. We are thankful to Scott Duberstein for helping us with
setting up Amazon Mechanical Turk tasks. We acknowledge partial support from the
National Science Foundation (NSF) award: CNS-1513721: “Context-Aware Harassment
Detection on Social Media”, the National Institute on Drug Abuse (NIDA) Grant No.
5R01DA039454- 02: “Trending: Social Media Analysis to Monitor Cannabis and Synthetic
Cannabinoid Use” and the National Institutes of Mental Health (NIMH) award:
1R01MH105384-01A1: “Modeling Social Behavior for Healthcare Utilization in
Depression”. Points of view or opinions in this document are those of the authors and
do not necessarily represent the official position or policies of the NSF, NIDA, or NIMH.