• Corpus ID: 244709137

Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models

@inproceedings{Venkit2021IdentificationOB,
  title={Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models},
  author={Pranav Venkit and Shomir Wilson},
  year={2021}
}
Sociodemographic biases are a common problem for natural language processing, affecting the fairness and integrity of its applications. Within sentiment analysis, these biases may undermine sentiment predictions for texts that mention personal attributes that unbiased human readers would consider neutral. Such discrimination can have great consequences in the applications of sentiment analysis both in the public and private sectors. For example, incorrect inferences in applications like online… 

Figures and Tables from this paper

Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias
TLDR
The attempt to draw a comprehensive view of bias in pre-trained language models, and especially the exploration of affective bias will be highly beneficial to researchers interested in this evolving field.

References

SHOWING 1-10 OF 57 REFERENCES
Addressing Age-Related Bias in Sentiment Analysis
TLDR
This study analyzes the treatment of age-related terms across 15 sentiment analysis models and 10 widely-used GloVe word embeddings and attempts to alleviate bias through a method of processing model training data.
Gender bias in sentiment analysis
TLDR
This is the first evidence that lexical sentiment analysis is less able to detect the opinions of one gender than another.
The Woman Worked as a Babysitter: On Biases in Language Generation
TLDR
The notion of the regard towards a demographic is introduced, the varying levels of regard towards different demographics are used as a defining metric for bias in NLG, and the extent to which sentiment scores are a relevant proxy metric for regard is analyzed.
Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems
TLDR
The Equity Evaluation Corpus (EEC) is presented, which consists of 8,640 English sentences carefully chosen to tease out biases towards certain races and genders, and it is found that several of the systems show statistically significant bias.
VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text
TLDR
Interestingly, using the authors' parsimonious rule-based model to assess the sentiment of tweets, it is found that VADER outperforms individual human raters, and generalizes more favorably across contexts than any of their benchmarks.
Social Biases in NLP Models as Barriers for Persons with Disabilities
TLDR
Evidence of undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis is presented and it is demonstrated that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases.
SentiBench - a benchmark comparison of state-of-the-practice sentiment analysis methods
TLDR
A benchmark comparison of twenty-four popular sentiment analysis methods, covering messages posted on social networks, movie and product reviews, as well as opinions and comments in news articles is presented, highlighting the extent to which the prediction performance of these methods varies considerably across datasets.
The Risk of Racial Bias in Hate Speech Detection
TLDR
This work proposes *dialect* and *race priming* as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet’s dialect they are significantly less likely to label the tweet as offensive.
Reducing Gender Bias in Abusive Language Detection
TLDR
Three mitigation methods, including debiased word embeddings, gender swap data augmentation, and fine-tuning with a larger corpus, can effectively reduce model bias by 90-98% and can be extended to correct model bias in other scenarios.
Hate Me, Hate Me Not: Hate Speech Detection on Facebook
TLDR
This work proposes a variety of hate categories and designs and implements two classifiers for the Italian language, based on different learning algorithms: the first based on Support Vector Machines (SVM) and the second on a particular Recurrent Neural Network named Long Short Term Memory (LSTM).
...
1
2
3
4
5
...