Contrastive Clustering: Toward Unsupervised Bias Reduction for Emotion and Sentiment Classification

11/14/2021
by   Jared Mowery, et al.
0

Background: When neural network emotion and sentiment classifiers are used in public health informatics studies, biases present in the classifiers could produce inadvertently misleading results. Objective: This study assesses the impact of bias on COVID-19 topics, and demonstrates an automatic algorithm for reducing bias when applied to COVID-19 social media texts. This could help public health informatics studies produce more timely results during crises, with a reduced risk of misleading results. Methods: Emotion and sentiment classifiers were applied to COVID-19 data before and after debiasing the classifiers using unsupervised contrastive clustering. Contrastive clustering approximates the degree to which tokens exhibit a causal versus correlational relationship with emotion or sentiment, by contrasting the tokens' relative salience to topics versus emotions or sentiments. Results: Contrastive clustering distinguishes correlation from causation for tokens with an F1 score of 0.753. Masking bias prone tokens from the classifier input decreases the classifier's overall F1 score by 0.02 (anger) and 0.033 (negative sentiment), but improves the F1 score for sentences annotated as bias prone by 0.155 (anger) and 0.103 (negative sentiment). Averaging across topics, debiasing reduces anger estimates by 14.4 8.0 Conclusions: Contrastive clustering reduces algorithmic bias in emotion and sentiment classification for social media text pertaining to the COVID-19 pandemic. Public health informatics studies should account for bias, due to its prevalence across a range of topics. Further research is needed to improve bias reduction techniques and to explore the adverse impact of bias on public health informatics analyses.

READ FULL TEXT
research
04/22/2022

Neural Contrastive Clustering: Fully Unsupervised Bias Reduction for Sentiment Classification

Background: Neural networks produce biased classification results due to...
research
03/07/2022

Emotion Regulation and Dynamics of Moral Concerns During the Early COVID-19 Pandemic

The COVID-19 pandemic has upended daily life around the globe, posing a ...
research
05/08/2020

Detecting East Asian Prejudice on Social Media

The outbreak of COVID-19 has transformed societies across the world as g...
research
06/24/2023

Characterizing the Emotion Carriers of COVID-19 Misinformation and Their Impact on Vaccination Outcomes in India and the United States

The COVID-19 Infodemic had an unprecedented impact on health behaviors a...
research
12/14/2020

"Thought I'd Share First": An Analysis of COVID-19 Conspiracy Theories and Misinformation Spread on Twitter

Background: Misinformation spread through social media is a growing prob...
research
12/22/2021

Multimodal Analysis of memes for sentiment extraction

Memes are one of the most ubiquitous forms of social media communication...
research
07/14/2020

COVID-19 Twitter Dataset with Latent Topics, Sentiments and Emotions Attributes

This paper presents a large annotated dataset on public expressions rela...

Please sign up or login with your details

Forgot password? Click here to reset