Unintended bias evaluation: An analysis of hate speech detection and gender bias mitigation on social media using ensemble learning

Nascimento, Francimaria R. S.; Cavalcanti, George D. C.; Abreu, Márjory Da Costa

doi:10.1016/j.eswa.2022.117032

Cited by 21 publications

(4 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through the research in this paper, although the analysis is in the media environment, what is reflected is the phenomenon in life, which is only expressed in the form of media, as Francimaria mentioned [9]. 'Sexism is typically based on the assumption that one sex or gender is superior to another.'…”

Section: Discussion and Suggestionsmentioning

confidence: 99%

Gender Stereotyping in Media - Bias and Discrimination

2023

LNEP

View full text Add to dashboard Cite

Gender stereotyping in media is a pervasive issue that refers to depictions of individuals or groups conforming to cultural expectations about gender roles and traits. Various forms of media, such as television, film, advertising, and social media, often present gender in stereotypical and limiting ways, perpetuating harmful societal norms. This perpetuation creates a cycle of gender bias and discrimination, affecting self-esteem, career opportunities, and overall well-being. These stereotypes can be damaging because they reinforce preconceived notions about masculinity and femininity. Efforts in the media industry aim to confront and modify these stereotypes through diverse and inclusive storytelling, promoting positive role models, and enhancing media literacy. Recognizing and challenging gender stereotypes in the media is crucial for promoting gender equality and dismantling harmful cultural practices. The article highlights the consequences of gender stereotyping in media, such as reinforcing traditional gender roles, objectification, and underrepresentation. It underscores the importance of media content creators, regulators, and consumers being aware of these biases and actively working toward more inclusive and equitable portrayals of gender.

show abstract

Section: Discussion and Suggestionsmentioning

confidence: 99%

Gender Stereotyping in Media - Bias and Discrimination

2023

LNEP

View full text Add to dashboard Cite

show abstract

“…In [21] authors proposed a method for automatic hate speech detection using a combination of natural language processing techniques and an ensemble deep learning approach. The proposed method involves pre-processing of text data, feature extraction using different techniques, and the use of a deep neural network ensemble model for classification.…”

Section: Literature Reviewmentioning

confidence: 99%

Hate Speech Detection in Social Media Using the Ensemble Learning Technique

Haque¹,

Chowdhury²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Hate speech detection from different languages has received significant attention within the research community. An ensemble learning technique which uses several feature spaces to learn from unintentional biased assessment measures was proposed in Nascimento et al (2022); for hate speech identification. A three-class instance-based approach in Pronoza et al (2021) was designed to detect ethnic hate speech on Russian social media text with a new three-class strategy.…”

Section: Introductionmentioning

confidence: 99%

An Optimal WordNet Based Emotional Word Extraction and Hybrid Deep Learning Classifier for Sentiment Analysis

Obare,

Ade-Ibijola,

Ogada

2023

IJDSBDA

View full text Add to dashboard Cite

Everyday, over one billion social media text messages are generated worldwide, which is a rich source of data that can lead to improvements in the lives of citizens through evidence-based decision making. Twitter is rich in such data but there are number of challenges in processing tweets with respect to volume, speed, ambiguity of the language in which tweets are written, which is an information extraction problem, in the domain of Natural Language Processing (NLP). While there is a growing interest in sentiment analysis for detecting emotions from tweets, there are no major efforts for detecting emotions that are disguised in tweets based on context of word usage, which is important for tasks such as identification of events such as hate speech, mental health related disorders. This paper presents a novel approach to context-based hate speech detection based on an optimal WordNet. Taking a modified Mayfly Optimization algorithm (MMO), we pre-process tweets and normalize the data using an NLP pipeline. We argument an improved Horse Herd Optimization algorithm (HHO) with WordNet and SentiWordNet to compute a tweet sentiment polarity. A hybrid Deep Belief Artificial Neural Network (hybrid DB-ANN) is then used to classify tweets. The performance of the proposed approach is compared to best known sentiment analysis algorithms using three standard benchmark datasets: Crowdflower-1, Crowdflower-2, and Kaggle Twitter. We demonstrate that the proposed approach outperforms industry benchmarks as it achieves over 90% in terms of accuracy, precision, recall, and F-measure.

show abstract

Unintended bias evaluation: An analysis of hate speech detection and gender bias mitigation on social media using ensemble learning

Cited by 21 publications

References 63 publications

Gender Stereotyping in Media - Bias and Discrimination

Gender Stereotyping in Media - Bias and Discrimination

Hate Speech Detection in Social Media Using the Ensemble Learning Technique

An Optimal WordNet Based Emotional Word Extraction and Hybrid Deep Learning Classifier for Sentiment Analysis

Contact Info

Product

Resources

About