Mitigating sentimental bias via a polar attention mechanism
| Autor: | Tao Yang, Ou Wu, Qiang Tian, Rujing Yao, Qing Yin |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
business.industry Polarity (physics) Computer science Applied Mathematics Sentiment analysis computer.software_genre Computer Science Applications 03 medical and health sciences 030104 developmental biology 0302 clinical medicine Distance measurement Computational Theory and Mathematics 030220 oncology & carcinogenesis Modeling and Simulation Polar Artificial intelligence Benchmark data business computer Natural language processing Word (computer architecture) Mechanism (sociology) Information Systems |
| Zdroj: | International Journal of Data Science and Analytics. 11:27-36 |
| ISSN: | 2364-4168 2364-415X |
| DOI: | 10.1007/s41060-020-00231-3 |
| Popis: | Fairness in machine learning has received increasing attention in recent years. This study focuses on a particular type of machine learning fairness, namely sentimental bias, in text sentiment analysis. Sentimental bias occurs on words (or phrases) when they are distributed distinctly in positive and negative corpora. It results in that an excessively proportion of words carry negative/positive sentiment in learned models. This study proposed a new attention mechanism, called polar attention, to mitigate sentimental biases. It consists of two modules, namely polar flipping and distance measurement. The first module explicitly models word sentimental polarity and can prevent that neutral words flip positively or negatively. The second module is used to attend negative/positive words. In the experiments, three benchmark data sets are used, and supplementary testing sets are compiled. Experimental results verify the effectiveness of the proposed method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink