EPUTION at SemEval-2018 Task 2: emoji prediction with user adaption

Liyuan Zhou; Qiongkai Xu; Hanna Suominen; Tom Gedeon

doi:10.18653/v1/s18-1071

EPUTION at SemEval-2018 Task 2: emoji prediction with user adaption

Liyuan Zhou, Qiongkai Xu, Hanna Suominen, Tom Gedeon

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

4 Citations (Scopus)

Abstract

This paper describes our approach, called EPUTION, for the open trial of the SemEval-2018 Task 2, Multilingual Emoji Prediction. The task relates to using social media - more precisely, Twitter - with its aim to predict the most likely associated emoji of a tweet. Our solution for this text classification problem explores the idea of transfer learning for adapting the classifier based on users' tweeting history. Our experiments show that our user-adaption method improves classification results by more than 6 per cent on the macro-averaged F1. Thus, our paper provides evidence for the rationality of enriching the original corpus longitudinally with user behaviors and transferring the lessons learned from corresponding users to specific instances.

Original language	English
Title of host publication	Proceedings of the 12th International Workshop on Semantic Evaluation
Place of Publication	Stroudsburg, PA
Publisher	Association for Computational Linguistics (ACL)
Pages	449-453
Number of pages	5
ISBN (Electronic)	9781948087209
DOIs	https://doi.org/10.18653/v1/s18-1071
Publication status	Published - 2018
Externally published	Yes
Event	12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the - New Orleans, United States Duration: 5 Jun 2018 → 6 Jun 2018

Conference

Conference	12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the
Country/Territory	United States
City	New Orleans
Period	5/06/18 → 6/06/18

Access to Document

10.18653/v1/s18-1071Licence: Unspecified

Cite this

@inproceedings{192d9c0afdcb49da8b061204e80ff23b,

title = "EPUTION at SemEval-2018 Task 2: emoji prediction with user adaption",

abstract = "This paper describes our approach, called EPUTION, for the open trial of the SemEval-2018 Task 2, Multilingual Emoji Prediction. The task relates to using social media - more precisely, Twitter - with its aim to predict the most likely associated emoji of a tweet. Our solution for this text classification problem explores the idea of transfer learning for adapting the classifier based on users' tweeting history. Our experiments show that our user-adaption method improves classification results by more than 6 per cent on the macro-averaged F1. Thus, our paper provides evidence for the rationality of enriching the original corpus longitudinally with user behaviors and transferring the lessons learned from corresponding users to specific instances.",

author = "Liyuan Zhou and Qiongkai Xu and Hanna Suominen and Tom Gedeon",

year = "2018",

doi = "10.18653/v1/s18-1071",

language = "English",

pages = "449--453",

booktitle = "Proceedings of the 12th International Workshop on Semantic Evaluation",

publisher = "Association for Computational Linguistics (ACL)",

address = "United States",

note = "12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the ; Conference date: 05-06-2018 Through 06-06-2018",

}

Zhou, L, Xu, Q, Suominen, H & Gedeon, T 2018, EPUTION at SemEval-2018 Task 2: emoji prediction with user adaption. in Proceedings of the 12th International Workshop on Semantic Evaluation. Association for Computational Linguistics (ACL), Stroudsburg, PA, pp. 449-453, 12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the, New Orleans, Louisiana, United States, 5/06/18. https://doi.org/10.18653/v1/s18-1071

EPUTION at SemEval-2018 Task 2: emoji prediction with user adaption. / Zhou, Liyuan; Xu, Qiongkai; Suominen, Hanna et al.
Proceedings of the 12th International Workshop on Semantic Evaluation. Stroudsburg, PA: Association for Computational Linguistics (ACL), 2018. p. 449-453.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - EPUTION at SemEval-2018 Task 2

T2 - 12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the

AU - Zhou, Liyuan

AU - Xu, Qiongkai

AU - Suominen, Hanna

AU - Gedeon, Tom

PY - 2018

Y1 - 2018

N2 - This paper describes our approach, called EPUTION, for the open trial of the SemEval-2018 Task 2, Multilingual Emoji Prediction. The task relates to using social media - more precisely, Twitter - with its aim to predict the most likely associated emoji of a tweet. Our solution for this text classification problem explores the idea of transfer learning for adapting the classifier based on users' tweeting history. Our experiments show that our user-adaption method improves classification results by more than 6 per cent on the macro-averaged F1. Thus, our paper provides evidence for the rationality of enriching the original corpus longitudinally with user behaviors and transferring the lessons learned from corresponding users to specific instances.

AB - This paper describes our approach, called EPUTION, for the open trial of the SemEval-2018 Task 2, Multilingual Emoji Prediction. The task relates to using social media - more precisely, Twitter - with its aim to predict the most likely associated emoji of a tweet. Our solution for this text classification problem explores the idea of transfer learning for adapting the classifier based on users' tweeting history. Our experiments show that our user-adaption method improves classification results by more than 6 per cent on the macro-averaged F1. Thus, our paper provides evidence for the rationality of enriching the original corpus longitudinally with user behaviors and transferring the lessons learned from corresponding users to specific instances.

UR - https://www.scopus.com/pages/publications/85102355473

U2 - 10.18653/v1/s18-1071

DO - 10.18653/v1/s18-1071

M3 - Conference proceeding contribution

SP - 449

EP - 453

BT - Proceedings of the 12th International Workshop on Semantic Evaluation

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg, PA

Y2 - 5 June 2018 through 6 June 2018

ER -

EPUTION at SemEval-2018 Task 2: emoji prediction with user adaption

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this