Zobraziť v EDS

Exploring hate speech detection: challenges, resources, current research and future directions.

Uložené v:
Podrobná bibliografia
Názov: Exploring hate speech detection: challenges, resources, current research and future directions.
Autori: Geetanjali, Kumar, Mohit
Zdroj: Multimedia Tools & Applications; Sep2025, Vol. 84 Issue 31, p38423-38459, 37p
Predmety: HATE speech, MACHINE learning, DEEP learning, ACQUISITION of data, INTERDISCIPLINARY research, DETECTION algorithms, NATURAL language processing
Abstrakt: The proliferation of online interactions has amplified the incidence of hate speech, presenting major obstacles to upkeep of a secure and welcoming digital environment. One of the primary obstacles lies in the diverse and dynamic nature of language, making it challenging to accurately define and classify hate speech. Existing data sets, while valuable, often lack comprehensive and may not encapsulate the evolving nuances of hate speech, necessitating continuous updates and expansions. Machine learning techniques, including traditional classifiers and natural language processing algorithms, have been instrumental in hate speech detection, leveraging features and patterns within textual data. However, these approaches sometimes struggle with context and sarcasm, limiting their efficacy. Deep learning techniques, particularly neural network models like recurrent and convolution architecture have shown promise in capturing intricate linguistic nuances and contextual cues, enhancing hate speech detection accuracy. Their reliance on extensive data and computational resources poses implementation challenges. Effort to combat hate speech demand interdisciplinary collaboration, combining linguistic expertise with technological advancements. Developing more comprehensive data sets reflective of diverse demographics and evolving language trends remains a crucial focus. Building trust and enabling the ethical deployment of machine learning and deep learning models requires improving their inter-pretability and explain-ability. While significant strides have been produced in hate speech detection, the multifaceted nature of language and the ever-evolving landscape of social media necessitate continued research to devise robust and adaptive solutions for a safer online environment. This survey attempts to offer a well-organized and thorough summary of the literature on the detection of hate speech. The survey also focus to analyze the hate speech papers published in last 10 years. Furthermore it aims to help researchers choose topics for future research and offer the research community empirical evidence and insights on the fundamental characteristics of hate speech. [ABSTRACT FROM AUTHOR]
Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Complementary Index
Popis
Abstrakt:The proliferation of online interactions has amplified the incidence of hate speech, presenting major obstacles to upkeep of a secure and welcoming digital environment. One of the primary obstacles lies in the diverse and dynamic nature of language, making it challenging to accurately define and classify hate speech. Existing data sets, while valuable, often lack comprehensive and may not encapsulate the evolving nuances of hate speech, necessitating continuous updates and expansions. Machine learning techniques, including traditional classifiers and natural language processing algorithms, have been instrumental in hate speech detection, leveraging features and patterns within textual data. However, these approaches sometimes struggle with context and sarcasm, limiting their efficacy. Deep learning techniques, particularly neural network models like recurrent and convolution architecture have shown promise in capturing intricate linguistic nuances and contextual cues, enhancing hate speech detection accuracy. Their reliance on extensive data and computational resources poses implementation challenges. Effort to combat hate speech demand interdisciplinary collaboration, combining linguistic expertise with technological advancements. Developing more comprehensive data sets reflective of diverse demographics and evolving language trends remains a crucial focus. Building trust and enabling the ethical deployment of machine learning and deep learning models requires improving their inter-pretability and explain-ability. While significant strides have been produced in hate speech detection, the multifaceted nature of language and the ever-evolving landscape of social media necessitate continued research to devise robust and adaptive solutions for a safer online environment. This survey attempts to offer a well-organized and thorough summary of the literature on the detection of hate speech. The survey also focus to analyze the hate speech papers published in last 10 years. Furthermore it aims to help researchers choose topics for future research and offer the research community empirical evidence and insights on the fundamental characteristics of hate speech. [ABSTRACT FROM AUTHOR]
ISSN:13807501
DOI:10.1007/s11042-025-20716-2