Publication

NUIG at EmoInt-2017: BiLSTM and SVR ensemble to detect emotion intensity

Andryushechkin, Vladimir
; 
Wood, Ian D.
; 
O'Neill, James
Thumbnail Image
Files
Thumbnail Image
BiLSTM_SVR_Ensemble_Emotion_Detection.pdf
Adobe PDF, 488.67 KB
Repository DOI
Publication Date
2017-09-08
Keywords
Emotion recognition, SVR, SVM regression, BiLSTM, Social media analysis
Type
Conference Paper
Downloads
Show all metadata
Citation
Andryushechkin, Vladimir, Wood, Ian David, & O’ Neill, James (2017). NUIG at EmoInt-2017: BiLSTM and SVR ensemble to detect emotion intensity. Paper presented at the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis WASSA 2017, Copenhagen, Denmark, 08 September.
Abstract
This paper describes the entry NUIG in the WASSA 20171 shared task on emotion recognition. The NUIG system used an SVR (SVM regression) and BiLSTM ensemble, utilizing primarily n-grams (for SVR features) and tweet word embeddings (for BiLSTM features). Experiments were carried out on several other candidate features, some of which were added to the SVR model. Parameter selection for the SVR model was run as a grid search whilst parameters for the BiLSTM model were selected through a non-exhaustive ad-hoc search.
Funder
Science Foundation Ireland
EU Horizon 2020
Publisher
Association for Computational Linguistics
Publisher DOI
Rights
Attribution-NonCommercial-NoDerivs 3.0 Ireland
cbn
Collections
Data Science Institute (Conference Papers)