Abstract
We present our methods and results for affect analysis in Twitter developed as a part of SemEval-2018 Task 1, where the sub-tasks involve predicting the intensity of emotion, the intensity of sentiment, and valence for tweets. For modeling, though we use a traditional LSTM network, we combine our model with several state-of-the-art techniques to improve its performance in a low-resource setting. For example, we use an encoder-decoder network to initialize the LSTM weights. Without any task specific optimization we achieve competitive results (macro-average Pearson correlation coefficient 0.696) in the El-reg task. In this paper, we describe our development strategy in detail along with an exposition of our results.- Anthology ID:
- S18-1054
- Volume:
- Proceedings of the 12th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Venues:
- SemEval | *SEM
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 358–363
- Language:
- URL:
- https://aclanthology.org/S18-1054
- DOI:
- 10.18653/v1/S18-1054
- Cite (ACL):
- Venkatesh Elango and Karan Uppal. 2018. RIDDL at SemEval-2018 Task 1: Rage Intensity Detection with Deep Learning. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 358–363, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- RIDDL at SemEval-2018 Task 1: Rage Intensity Detection with Deep Learning (Elango & Uppal, SemEval-*SEM 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/S18-1054.pdf