SeerNet at SemEval-2018 Task 1: Domain Adaptation for Affect in Tweets
Abstract
The paper describes the best performing system for the SemEval-2018 Affect in Tweets (English) sub-tasks. The system focuses on the ordinal classification and regression sub-tasks for valence and emotion. For ordinal classification valence is classified into 7 different classes ranging from -3 to 3 whereas emotion is classified into 4 different classes 0 to 3 separately for each emotion namely anger, fear, joy and sadness. The regression sub-tasks estimate the intensity of valence and each emotion. The system performs domain adaptation of 4 different models and creates an ensemble to give the final prediction. The proposed system achieved 1st position out of 75 teams which participated in the fore-mentioned sub-tasks. We outperform the baseline model by margins ranging from 49.2% to 76.4%, thus, pushing the state-of-the-art significantly.
Keywords
Cite
@article{arxiv.1804.06137,
title = {SeerNet at SemEval-2018 Task 1: Domain Adaptation for Affect in Tweets},
author = {Venkatesh Duppada and Royal Jain and Sushant Hiray},
journal= {arXiv preprint arXiv:1804.06137},
year = {2018}
}
Comments
SemEval-2018 Task 1: Affect in Tweets