Background: Neural networks produce biased classification results due to correlation bias (they learn correlations between their inputs and outputs to classify samples, even when those correlations do not represent cause-and-effect relationships). Objective: This study introduces a fully unsupervised method of mitigating correlation bias, demonstrated with sentiment classification on COVID-19 social media data. Methods: Correlation bias in sentiment classification often arises in conversations about controversial topics. Therefore, this study uses adversarial learning to contrast clusters based on sentiment classification labels, with clusters produced by unsupervised topic modeling. This discourages the neural network from learning topic-related features that produce biased classification results. Results: Compared to a baseline classifier, neural contrastive clustering approximately doubles accuracy on bias-prone sentences for human-labeled COVID-19 social media data, without adversely affecting the classifier's overall F1 score. Despite being a fully unsupervised approach, neural contrastive clustering achieves a larger improvement in accuracy on bias-prone sentences than a supervised masking approach. Conclusions: Neural contrastive clustering reduces correlation bias in sentiment text classification. Further research is needed to explore generalizing this technique to other neural network architectures and application domains.

翻译：神经网络因相关偏差而产生偏差分类结果:神经网络因相关偏差(它们学习其投入和产出之间的关联,以对样本进行分类,即使这些关联并不代表因果关系)。 目标:本研究采用了完全不受监督的减轻相关偏差的方法,在COVID-19社交媒体数据中表现了情绪分类。方法:情绪分类中的关联偏差经常在有关有争议的议题的谈话中产生。因此,本研究采用对抗性学习,以情绪分类标签为基础,对比群集,由不受监督的专题模型生成的群集。这不利于神经网络学习产生偏差分类结果的专题相关特征。结果:与基线分类器相比,神经对比组合对人标的COVID-19社交媒体数据中偏差判决的精度大约是双倍的反向组合,但不会对分类者的总体F1评分产生不利影响。尽管这是完全不受监督的方法,但神经对比组合在偏差性判决的准确度方面比受监督的模范式混合方法得到更大的改进。结论:神经对比组合减少了情绪文字分类中的相对偏差。需要进一步研究,以便探索其他网络应用。