research-article

What Does Your Tweet Emotion Mean?: Neural Emoji Prediction for Sentiment Analysis

Authors:

Toshiki Tomihira,

Atsushi Otsuka,

Akihiro Yamashita,

Tetsuji SatohAuthors Info & Claims

iiWAS2018: Proceedings of the 20th International Conference on Information Integration and Web-based Applications & Services

Pages 289 - 296

https://doi.org/10.1145/3282373.3282406

Published: 19 November 2018 Publication History

Abstract

In recent years, Unicode has been standardized; and with the penetration of SNSs, the use of emojis has become common. Emojis, as they are also known, are most efective in expressing emotions in sentences. Sentiment analysis in natural language processing so far has involved learning by manual labeling of sentences. By using suitable emojis estimated from sentences, people might express their emotions more clearly and laconically. In this paper, we propose a new model that learns from sentences using emojis as labels, collecting Japanese tweets from Twitter as the corpus. We verify and compare multiple models based on EncoderDecoder Model of Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN). Our sophisticated experiments demonstrate that emojis are efective in expressing tweet emotion.

References

[1]

"Archive Team," https://archive.org/details/twitterstream

[2]

GERS, Felix A.; SCHMIDHUBER, Jürgen; CUMMINS, Fred. Learning to forget: Continual prediction with LSTM. 1999.

[3]

KRIZHEVSKY, Alex; SUTSKEVER, Ilya; HINTON, Geoffrey E. Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. 2012. p. 1097--1105.

Digital Library

[4]

Yoon Kim, "Convolutional Neural Networks for Sentence Classification", arXiv preprint arXiv, 2014.

[5]

Ye Zhang, Byron Wallace,"A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification", arXiv preprint arXiv, 2016.

[6]

NIKHIL, Nishant; SRIVASTAVA, Muktabh Mayank. Binarizer at SemEval-2018 Task 3: Parsing dependency and deep learning for irony detection. arXiv preprint arXiv:1805.01112, 2018.

[7]

NADERI, Habibeh, et al. DeepMiner at SemEval-2018 Task 1: Emotion Intensity Recognition Using Deep Representation Learning.

[8]

In: Proceedings of The 12th International Workshop on Semantic Evaluation. 2018. p. 305--312. KARTHIK, Valmeekam; NAIR, Dheeraj; ANURADHA, J. Opinion Mining on Emojis using Deep Learning Techniques. Procedia Computer Science, 2018, 132: 167--173.

[9]

LU, Xingwu, et al. ECNU at SemEval-2018 Task 2: Leverage Traditional NLP Features and Neural Networks Methods to Address Twitter Emoji Prediction Task. In: Proceedings of The 12th International Workshop on Semantic Evaluation. 2018. p. 433--437.

[10]

CHEN, Zhenpeng, et al. Ermes: Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification. arXiv preprint arXiv:1806.02557, 2018.

[11]

MALIK, Vikas; KUMAR, Amit. Analysis of Twitter Data Using Deep Learning Approach: LSTM. International Journal on Recent and Innovation Trends in Computing and Communication, 2018, 6.4: 144--149.

[12]

CHOUDHARY, Nurendra, et al. Contrastive Learning of Emoji-based Representations for Resource-Poor Languages. arXiv preprint arXiv:1804.01855, 2018.

[13]

BAZIOTIS, Christos, et al. NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning. arXiv preprint arXiv:1804.06658, 2018.

[14]

BAZIOTIS, Christos, et al. NTUA-SLP at SemEval-2018 Task 2: Predicting Emojis using RNNs with Context-aware Attention. arXiv preprint arXiv:1804.06657, 2018.

[15]

ALEXA, Larisa, et al. The Dabblers at SemEval-2018 Task 2: Multilingual Emoji Prediction. In: Proceedings of The 12th International Workshop on Semantic Evaluation. 2018. p. 405--409.

[16]

PARK, Ji Ho; XU, Peng; FUNG, Pascale. PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and hashtags. arXiv preprint arXiv:1804.08280, 2018.

[17]

FELBO, Bjarke, et al. Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm. arXiv preprint arXiv:1708.00524, 2017.

[18]

BARBIERI, Francesco, et al. Multimodal emoji prediction. arXiv preprint arXiv:1803.02392, 2018.

[19]

BARBIERI, Francesco, et al. Multi-task Emoji Learning. 2018.

[20]

EISNER, Ben, et al. emoji2vec: Learning emoji representations from their description. arXiv preprint arXiv:1609.08359, 2016.

[21]

BARBIERI, Francesco; BALLESTEROS, Miguel; SAGGION, Horacio. Are Emojis Predictable?. arXiv preprint arXiv:1702.07285, 2017.

[22]

ZHAO, Luda; ZENG, Connie. Using Neural Networks to Predict Emoji Usage from Twitter Data.

[23]

BARBIERI, Francesco, et al. SemEval 2018 Task 2: Multilingual Emoji Prediction. In: Proceedings of The 12th International Workshop on Semantic Evaluation. 2018. p. 24--33.

[24]

KOPEV, Daniel, et al. Tweety at SemEval-2018 Task 2: Predicting Emojis using Hierarchical Attention Neural Networks and Support Vector Machine. In: Proceedings of The 12th International Workshop on Semantic Evaluation. 2018. p. 497--501.

[25]

T. Mikolov, K. Chen, G. Corrado, J. Dean, "Efficient estimation of word representations in vector space," arXiv preprint arXiv, 2013.

[26]

MIKOLOV, Tomas; LE, Quoc V.; SUTSKEVER, Ilya. Exploiting similarities among languages for machine translation. arXiv preprint arXiv:1309.4168, 2013.

[27]

CHO, Kyunghyun, et al. Learning phrase representations using RNN encoderdecoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014.

[28]

SUNDERMEYER, Martin; SCHLÜTER, Ralf; NEY, Hermann. LSTM neural networks for language modeling. In: Thirteenth annual conference of the international speech communication association. 2012.

[29]

SUTSKEVER, Ilya; VINYALS, Oriol; LE, Quoc V. Sequence to sequence learning with neural networks. In: Advances in neural information processing systems. 2014. p. 3104--3112.

Digital Library

[30]

BAHDANAU, Dzmitry; CHO, Kyunghyun; BENGIO, Yoshua. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014.

[31]

VINYALS, Oriol; LE, Quoc. A neural conversational model. arXiv preprint arXiv:1506.05869, 2015.

[32]

"Mecab: Yet another part-of-speech and morphological an- alyzer", http://mecab.sourceforge.net/ (2005).

[33]

"mecab-ipadic-neologd: Neologism dictionary for mecab", https://github.com/neologd/mecab-ipadic-neologd.

[34]

BOJANOWSKI, Piotr, et al. Enriching word vectors with subword information. arXiv preprint arXiv:1607.04606, 2016.

[35]

Atsushi Otsuka Katsuhito, et al. Proposal of a document retrieval method to pre-read answers. DEIM Forum: B6-3 2017.

Cited By

Kone VAnagal AAnegundi SJadekar PPatil P(2023)Emoji Prediction Using Bi-Directional LSTMITM Web of Conferences10.1051/itmconf/2023530200453(02004)Online publication date: 1-Jun-2023
https://doi.org/10.1051/itmconf/20235302004
Thakur N(2022)Twitter Big Data as a Resource for Exoskeleton Research: A Large-Scale Dataset of about 140,000 Tweets from 2017–2022 and 100 Research QuestionsAnalytics10.3390/analytics10200071:2(72-97)Online publication date: 23-Sep-2022
https://doi.org/10.3390/analytics1020007
Himabindu GRao RSethia D(2022)A self-attention hybrid emoji prediction model for code-mixed language: (Hinglish)Social Network Analysis and Mining10.1007/s13278-022-00961-112:1Online publication date: 14-Sep-2022
https://doi.org/10.1007/s13278-022-00961-1
Show More Cited By

Index Terms

What Does Your Tweet Emotion Mean?: Neural Emoji Prediction for Sentiment Analysis

Recommendations

Emoji-Based Sentiment Analysis Using Attention Networks

Emojis are frequently used to express moods, emotions, and feelings in social media. There has been much research on emojis and sentiments. However, existing methods mainly face two limitations. First, they treat emojis as binary indicator features and ...
Deep Learning and Ensemble Approach for Praise or Complaint Classification
Abstract
Online reviews, social media data contains wealth of information about customer’s likes and dislikes about product or service. Extreme opinions in terms of praises and complaints are more informative as compared to plain positive and plain ...
Investigating the Consistency of Emoji Sentiment Lexicons Constructed Using Different Languages
iiWAS2018: Proceedings of the 20th International Conference on Information Integration and Web-based Applications & Services

Emojis have been widely used in recent text-based communications and can be important features for sentiment analysis of social media posts such as tweets. Our previous work presented a method for automatically constructing an emoji sentiment lexicon ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

iiWAS2018: Proceedings of the 20th International Conference on Information Integration and Web-based Applications & Services

November 2018

419 pages

ISBN:9781450364799

DOI:10.1145/3282373

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Johannes Kepler University, Linz, Austria
@WAS: International Organization of Information Integration and Web-based Applications and Services
Johannes Kepler University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 November 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

iiWAS2018

iiWAS2018: 20th International Conference on Information Integration and Web-based Applications & Services

November 19 - 21, 2018

Yogyakarta, Indonesia

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
393
Total Downloads

Downloads (Last 12 months)30
Downloads (Last 6 weeks)2

Reflects downloads up to 13 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Kone VAnagal AAnegundi SJadekar PPatil P(2023)Emoji Prediction Using Bi-Directional LSTMITM Web of Conferences10.1051/itmconf/2023530200453(02004)Online publication date: 1-Jun-2023
https://doi.org/10.1051/itmconf/20235302004
Thakur N(2022)Twitter Big Data as a Resource for Exoskeleton Research: A Large-Scale Dataset of about 140,000 Tweets from 2017–2022 and 100 Research QuestionsAnalytics10.3390/analytics10200071:2(72-97)Online publication date: 23-Sep-2022
https://doi.org/10.3390/analytics1020007
Himabindu GRao RSethia D(2022)A self-attention hybrid emoji prediction model for code-mixed language: (Hinglish)Social Network Analysis and Mining10.1007/s13278-022-00961-112:1Online publication date: 14-Sep-2022
https://doi.org/10.1007/s13278-022-00961-1
Vieira JRocha RPereira LVanderlei IAraujo JDantas J(2022)bNaming: An Intelligent Application to Assist Brand Names DefinitionInformation Integration and Web Intelligence10.1007/978-3-031-21047-1_6(75-89)Online publication date: 20-Nov-2022
https://doi.org/10.1007/978-3-031-21047-1_6
Saha UMahmud MKeya MLucky EKhushbu SNoori SSyed M(2022)Exploring Public Attitude Towards Children by Leveraging Emoji to Track Out Sentiment Using Distil-BERT a Fine-Tuned ModelThird International Conference on Image Processing and Capsule Networks10.1007/978-3-031-12413-6_26(332-346)Online publication date: 29-Jul-2022
https://doi.org/10.1007/978-3-031-12413-6_26
Tembhurne JDiwan T(2020)Sentiment analysis in textual, visual and multimodal inputs using recurrent neural networksMultimedia Tools and Applications10.1007/s11042-020-10037-xOnline publication date: 22-Oct-2020
https://doi.org/10.1007/s11042-020-10037-x
Phan HTran VNguyen NHwang D(2020)A Framework for Detecting User’s Psychological Tendencies on Twitter Based on Tweets Sentiment AnalysisTrends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices10.1007/978-3-030-55789-8_32(357-372)Online publication date: 4-Sep-2020
https://doi.org/10.1007/978-3-030-55789-8_32
Naskar DOnaindia ERebollo MDas S(2019)Modelling Emotion Dynamics on Twitter via Hidden Markov ModelProceedings of the 21st International Conference on Information Integration and Web-based Applications & Services10.1145/3366030.3366092(245-249)Online publication date: 2-Dec-2019
https://dl.acm.org/doi/10.1145/3366030.3366092
Liebeskind CLiebeskind S(2019)Emoji Prediction for Hebrew Political DomainCompanion Proceedings of The 2019 World Wide Web Conference10.1145/3308560.3316548(468-477)Online publication date: 13-May-2019
https://dl.acm.org/doi/10.1145/3308560.3316548

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents