EmotiKLUE at IEST 2018: Topic-Informed Classification of Implicit Emotions

Thomas Proisl, Philipp Heinrich, Besim Kabashi, Stefan Evert


Abstract
EmotiKLUE is a submission to the Implicit Emotion Shared Task. It is a deep learning system that combines independent representations of the left and right contexts of the emotion word with the topic distribution of an LDA topic model. EmotiKLUE achieves a macro average F₁score of 67.13%, significantly outperforming the baseline produced by a simple ML classifier. Further enhancements after the evaluation period lead to an improved F₁score of 68.10%.
Anthology ID:
W18-6234
Volume:
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
235–242
Language:
URL:
https://aclanthology.org/W18-6234
DOI:
10.18653/v1/W18-6234
Bibkey:
Cite (ACL):
Thomas Proisl, Philipp Heinrich, Besim Kabashi, and Stefan Evert. 2018. EmotiKLUE at IEST 2018: Topic-Informed Classification of Implicit Emotions. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 235–242, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
EmotiKLUE at IEST 2018: Topic-Informed Classification of Implicit Emotions (Proisl et al., WASSA 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/W18-6234.pdf
Code
 tsproisl/EmotiKLUE