HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets

Wen Ting Wang; Man Lan

doi:10.18653/v1/P17

HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets

Wen Ting Wang, Man Lan

School of Computer Science and Technology

Alibaba Group Holding Ltd.

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

3 Scopus citations

Abstract

This paper describes our system designed for the WASSA-2018 Implicit Emotion Shared Task (IEST). The task is to predict the emotion category expressed in a tweet by removing the terms angry, afraid, happy, sad, surprised, disgusted and their synonyms. Our final submission is an ensemble of one supervised learning model and three deep neural network based models, where each model approaches the problem from essentially different directions. Our system achieves the macro F1 score of 65.8%, which is a 5.9% performance improvement over the baseline and is ranked 12 out of 30 participating teams.

Original language	English
Title of host publication	WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	205-210
Number of pages	6
ISBN (Electronic)	9781948087803
DOIs	https://doi.org/10.18653/v1/P17
State	Published - 2018
Event	9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2018 - Brussels, Belgium Duration: 31 Oct 2018 → …

Publication series

Name	WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop

Conference

Conference	9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2018
Country/Territory	Belgium
City	Brussels
Period	31/10/18 → …

Access to Document

10.18653/v1/P17

Cite this

Wang, W. T., & Lan, M. (2018). HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets. In WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop (pp. 205-210). (WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17

Wang, Wen Ting ; Lan, Man. / HGSGNLP at IEST 2018 : An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets. WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2018. pp. 205-210 (WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop).

@inproceedings{881bb03654834e658187811a26ee3746,

title = "HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets",

abstract = "This paper describes our system designed for the WASSA-2018 Implicit Emotion Shared Task (IEST). The task is to predict the emotion category expressed in a tweet by removing the terms angry, afraid, happy, sad, surprised, disgusted and their synonyms. Our final submission is an ensemble of one supervised learning model and three deep neural network based models, where each model approaches the problem from essentially different directions. Our system achieves the macro F1 score of 65.8\%, which is a 5.9\% performance improvement over the baseline and is ranked 12 out of 30 participating teams.",

author = "Wang, \{Wen Ting\} and Man Lan",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2018 ; Conference date: 31-10-2018",

year = "2018",

doi = "10.18653/v1/P17",

language = "英语",

series = "WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop",

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

pages = "205--210",

booktitle = "WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop",

address = "澳大利亚",

}

Wang, WT & Lan, M 2018, HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets. in WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop. WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop, Association for Computational Linguistics (ACL), pp. 205-210, 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2018, Brussels, Belgium, 31/10/18. https://doi.org/10.18653/v1/P17

HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets. / Wang, Wen Ting; Lan, Man.
WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2018. p. 205-210 (WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop).

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

TY - GEN

T1 - HGSGNLP at IEST 2018

T2 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2018

AU - Wang, Wen Ting

AU - Lan, Man

PY - 2018

Y1 - 2018

N2 - This paper describes our system designed for the WASSA-2018 Implicit Emotion Shared Task (IEST). The task is to predict the emotion category expressed in a tweet by removing the terms angry, afraid, happy, sad, surprised, disgusted and their synonyms. Our final submission is an ensemble of one supervised learning model and three deep neural network based models, where each model approaches the problem from essentially different directions. Our system achieves the macro F1 score of 65.8%, which is a 5.9% performance improvement over the baseline and is ranked 12 out of 30 participating teams.

AB - This paper describes our system designed for the WASSA-2018 Implicit Emotion Shared Task (IEST). The task is to predict the emotion category expressed in a tweet by removing the terms angry, afraid, happy, sad, surprised, disgusted and their synonyms. Our final submission is an ensemble of one supervised learning model and three deep neural network based models, where each model approaches the problem from essentially different directions. Our system achieves the macro F1 score of 65.8%, which is a 5.9% performance improvement over the baseline and is ranked 12 out of 30 participating teams.

UR - https://www.scopus.com/pages/publications/85122308104

U2 - 10.18653/v1/P17

DO - 10.18653/v1/P17

M3 - 会议稿件

AN - SCOPUS:85122308104

T3 - WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop

SP - 205

EP - 210

BT - WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop

PB - Association for Computational Linguistics (ACL)

Y2 - 31 October 2018

ER -

Wang WT, Lan M. HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets. In WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2018. p. 205-210. (WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop). doi: 10.18653/v1/P17

HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this