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.- Anthology ID:
- W18-6229
- Volume:
- Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Alexandra Balahur, Saif M. Mohammad, Veronique Hoste, Roman Klinger
- Venue:
- WASSA
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 205–210
- Language:
- URL:
- https://aclanthology.org/W18-6229
- DOI:
- 10.18653/v1/W18-6229
- Cite (ACL):
- Wenting Wang. 2018. HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 205–210, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- HGSGNLP at IEST 2018: An Ensemble of Machine Learning and Deep Neural Architectures for Implicit Emotion Classification in Tweets (Wang, WASSA 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/W18-6229.pdf