Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance
arXiv:2008.11573 · doi:10.1109/TNNLS.2021.3094304
Abstract
We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics and social sciences. In particular, we introduce a sentiment analysis framework in multi-label setting as it obeys Plutchik's wheel of emotions. We introduce a novel dynamic weighting method that balances the contribution from each class during training, unlike previous static weighting methods that assign non-changing weights based on their class frequency. Moreover, we adapt the focal loss that favors harder instances from single-label object recognition literature to our multi-label setting. Furthermore, we derive a method to choose optimal class-specific thresholds that maximize the macro-f1 score in linear time complexity. Through an extensive set of experiments, we show that our method obtains the state-of-the-art performance in 7 of 9 metrics in 3 different languages using a single model compared to the common baselines and the best-performing methods in the SemEval competition. We publicly share our code for our model, which can perform sentiment analysis in 100 languages, to facilitate further research.
arXiv comment12 pages, 4 figures, 4 tables. Accepted version of the article published in IEEE Transactions on Neural Networks and Learning Systems
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Distributed Representations of Words and Phrases and their Compositionality
- Natural Language Processing (almost) from Scratch
- Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm
- Enriching Word Vectors with Subword Information
- Practical Text Classification With Large Pre-Trained Language Models