Detecting Hate Speech on Social Media with Respect to Adolescent Vulnerability

Chiu, Anna; Sood, Kanika; Rincon, Ariadne; Doran, Davina

doi:10.1109/ccwc57344.2023.10099373

Cited by 5 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there remains a risk of biases from the training data translating to the generated letters. Racial and sex biases were reported for GPT-3, 26 although with the added human feedback loop, some of these were addressed for ChatGPT. However, not all bias is as easy to detect, and there is an additional risk of an adversary intentionally introducing biases to favour or cause harm to certain patient groups.…”

Section: Discussionmentioning

confidence: 99%

Application of generative language models to orthopaedic practice

Caterson,

Ambler,

Cereceda-Monteoliva

et al. 2024

BMJ Open

View full text Add to dashboard Cite

ObjectiveTo explore whether large language models (LLMs) Generated Pre-trained Transformer (GPT)-3 and ChatGPT can write clinical letters and predict management plans for common orthopaedic scenarios.DesignFifteen scenarios were generated and ChatGPT and GPT-3 prompted to write clinical letters and separately generate management plans for identical scenarios with plans removed.Main outcome measuresLetters were assessed for readability using the Readable Tool. Accuracy of letters and management plans were assessed by three independent orthopaedic surgery clinicians.ResultsBoth models generated complete letters for all scenarios after single prompting. Readability was compared using Flesch-Kincade Grade Level (ChatGPT: 8.77 (SD 0.918); GPT-3: 8.47 (SD 0.982)), Flesch Readability Ease (ChatGPT: 58.2 (SD 4.00); GPT-3: 59.3 (SD 6.98)), Simple Measure of Gobbledygook (SMOG) Index (ChatGPT: 11.6 (SD 0.755); GPT-3: 11.4 (SD 1.01)), and reach (ChatGPT: 81.2%; GPT-3: 80.3%). ChatGPT produced more accurate letters (8.7/10 (SD 0.60) vs 7.3/10 (SD 1.41), p=0.024) and management plans (7.9/10 (SD 0.63) vs 6.8/10 (SD 1.06), p<0.001) than GPT-3. However, both LLMs sometimes omitted key information or added additional guidance which was at worst inaccurate.ConclusionsThis study shows that LLMs are effective for generation of clinical letters. With little prompting, they are readable and mostly accurate. However, they are not consistent, and include inappropriate omissions or insertions. Furthermore, management plans produced by LLMs are generic but often accurate. In the future, a healthcare specific language model trained on accurate and secure data could provide an excellent tool for increasing the efficiency of clinicians through summarisation of large volumes of data into a single clinical letter.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of generative language models to orthopaedic practice

Caterson,

Ambler,

Cereceda-Monteoliva

et al. 2024

BMJ Open

View full text Add to dashboard Cite

show abstract

“…Despite promising outcomes in detecting hate speech, particularly achieving an approximate 80% accuracy compared to MTurker annotations (Li et al, 2023), it is imperative to explore the model's limitations to ensure its reliability and robustness. Chiu et al (2021) examined whether large language models like GPT-3 could detect and classify hate speech, particularly focusing on sexist and racist text targeting marginalized groups. They looked into several learning strategies, such as few-shot, zero-shot, and one-shot learning.…”

Section: Deep Learning Techniquesmentioning

confidence: 99%

“…Race (Mathew et al, n.d.;Alatawi et al, 2021;Chiu et al, 2021;MacAvaney et al, 2019;Sajid et al, 2020;Shannaq et al, 2022;Sharma & Shrivastava, 2018;Zhang & Luo, 2018) Religion (Sajid et al, 2020;Zhang & Luo, 2018), (Mathew et al, n.d.;Ali et al, 2021;Mozafari et al, 2022;Qureshi & Sabih, 2021) Ethnicity (Ali et al, 2021;Ghosh et al, 2023;Mozafari et al, 2022;Pronoza et al, 2021;Watanabe et al, 2018) Sexist (Al-Hassan & Al-Dossari, 2022;Baydogan & Alatas, 2021;Chiu et al, 2021;MacAvaney et al, 2019;Mozafari et al, 2022;Qureshi & Sabih, 2021;Shannaq et al, 2022) Political (Govers et al, 2023;Oriola & Kotze, 2020;Plaza-Del-Arco et al, 2021;Ribeiro et al, 2017;Wang et al, 2022) Women and immigrants (Irani et al, 2021;MacAvaney et al, 2019;Zhou et al, 2020) Covid-19 (Ahmed & Lin, 2022;Khanday et al, 2022;Su et al, 2023) Gender (Ghosh et al, 2023) Crime (Mathew et al, n.d.) and those addressing hate speech within the framework of the COVID-19 outbreak, such as Khanday et al (2022) and…”

Section: Target Studymentioning

confidence: 99%

Hate speech detection in social media: Techniques, recent trends, and future challenges

Rawat,

Kumar,

Samant

2024

WIREs Computational Stats

View full text Add to dashboard Cite

The realm of Natural Language Processing and Text Mining has seen a surge in interest from researchers in hate speech detection, leading to an increase in related studies. This analysis aims to create a valuable resource by summarizing the methods and strategies used to combat hate speech in social media. We perform a detailed review to achieve a deep knowledge of the hate speech detection landscape from 2018 to 2023, revealing global incidents of hate speech in 2022–2023. Sixty‐six relevant articles were selected for this review. Existing studies were analyzed and categorized into five method categories: Machine Learning, Deep Learning, Ensemble models, Graph Neural Networks, and Graph Convolutional Networks. These advancements can aid social networking services in identifying hate messages before being posted, reducing the risk of harassment. The review also covers available hate speech datasets and highlights research challenges, but it is clear that a definitive solution to this problem is yet to be found. Future research directions are recommended to address the ongoing challenges in Hate Speech Detection.This article is categorized under: Applications of Computational Statistics > Computational Linguistics Statistical Learning and Exploratory Methods of the Data Sciences > Knowledge Discovery Statistical Learning and Exploratory Methods of the Data Sciences > Classification and Regression Trees (CART) Statistical Learning and Exploratory Methods of the Data Sciences > Text Mining

show abstract

Sentiment Analysis of Hate Speech on Women in Social Media Platform Using Multi Label Classification

Pillala,

Ramana

2024

Ann. Data. Sci.

View full text Add to dashboard Cite

Detecting Hate Speech on Social Media with Respect to Adolescent Vulnerability

Cited by 5 publications

References 7 publications

Application of generative language models to orthopaedic practice

Application of generative language models to orthopaedic practice

Hate speech detection in social media: Techniques, recent trends, and future challenges

Sentiment Analysis of Hate Speech on Women in Social Media Platform Using Multi Label Classification

Contact Info

Product

Resources

About