scholarly journals Towards generalisable hate speech detection: a review on obstacles and solutions

2021 ◽  
Vol 7 ◽  
pp. e598
Author(s):  
Wenjie Yin ◽  
Arkaitz Zubiaga
Keyword(s):  
Natural Language Processing ◽  
Sexual Orientation ◽  
Language Processing ◽  
Hate Speech ◽  
Future Research ◽  
Individual Member ◽  
Speech Detection ◽  
Survey Paper ◽  
Unseen Data ◽  
Natural Language Processing Task

Hate speech is one type of harmful online content which directly attacks or promotes hate towards a group or an individual member based on their actual or perceived aspects of identity, such as ethnicity, religion, and sexual orientation. With online hate speech on the rise, its automatic detection as a natural language processing task is gaining increasing interest. However, it is only recently that it has been shown that existing models generalise poorly to unseen data. This survey paper attempts to summarise how generalisable existing hate speech detection models are and the reasons why hate speech models struggle to generalise, sums up existing attempts at addressing the main obstacles, and then proposes directions of future research to improve generalisation in hate speech detection.

Research Journey of Hate Content Detection From Cyberspace

2021 ◽  
pp. 200-225
Author(s):  
Sayani Ghosal ◽  
Amita Jain
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Digital Media ◽  
Language Processing ◽  
Social Networking Sites ◽  
Hate Speech ◽  
Detection System ◽  
Machine Learning Algorithms ◽  
Speech Detection ◽  
Healthy Environment

Hate content detection is the most prospective and challenging research area under the natural language processing domain. Hate speech abuse individuals or groups of people based on religion, caste, language, or sex. Enormous growth of digital media and cyberspace has encouraged researchers to work on hatred speech detection. A commonly acceptable automatic hate detection system is required to stop flowing hate-motivated data. Anonymous hate content is affecting the young generation and adults on social networking sites. Through numerous studies and review papers, the chapter identifies the need for artificial intelligence (AI) in hate speech research. The chapter explores the current state-of-the-art and prospects of AI in natural language processing (NLP) and machine learning algorithms. The chapter aims to identify the most successful methods or techniques for hate speech detection to date. Revolution in this research helps social media to provide a healthy environment for everyone.

scholarly journals Multimodal Hate Speech Detection in Greek Social Media

2021 ◽  
Vol 5 (7) ◽  
pp. 34
Author(s):  
Konstantinos Perifanos ◽  
Dionysis Goutsos
Keyword(s):  
Social Media ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Hate Speech ◽  
Language Model ◽  
Fine Tuning ◽  
Accuracy Score ◽  
Speech Detection ◽  
Online Social Media

Hateful and abusive speech presents a major challenge for all online social media platforms. Recent advances in Natural Language Processing and Natural Language Understanding allow for more accurate detection of hate speech in textual streams. This study presents a new multimodal approach to hate speech detection by combining Computer Vision and Natural Language processing models for abusive context detection. Our study focuses on Twitter messages and, more specifically, on hateful, xenophobic, and racist speech in Greek aimed at refugees and migrants. In our approach, we combine transfer learning and fine-tuning of Bidirectional Encoder Representations from Transformers (BERT) and Residual Neural Networks (Resnet). Our contribution includes the development of a new dataset for hate speech classification, consisting of tweet IDs, along with the code to obtain their visual appearance, as they would have been rendered in a web browser. We have also released a pre-trained Language Model trained on Greek tweets, which has been used in our experiments. We report a consistently high level of accuracy (accuracy score = 0.970, f1-score = 0.947 in our best model) in racist and xenophobic speech detection.

scholarly journals Comparison of Two Forced Alignments Systems for Aligning Bribri Speech

2017 ◽  
Author(s):  
Sofía Flores Solórzano ◽  
Rolando Coto-Solano
Keyword(s):  
Natural Language Processing ◽  
Speech Recognition ◽  
Language Processing ◽  
Indigenous Languages ◽  
Future Research ◽  
Automated Speech Recognition ◽  
Recognition Systems ◽  
Para Determinar ◽  
Future Work ◽  
Manual Correction

Abstract: Forced alignment provides drastic savings in time when aligning speech recordings and is particularly useful for the study of Indigenous languages, which are severely under-resourced in corpora and models. Here we compare two forced alignment systems, FAVE-align and EasyAlign, to determine which one provides more precision when processing running speech in the Chibchan language Bribri. We aligned a segment of a story narrated in Bribri and compared the errors in finding the center of the words and the edges of phonemes when compared with the manual correction. FAVE-align showed better performance: It has an error of 7% compared to 24% with EasyAlign when finding the center of words, and errors of 22~24 ms when finding the edges of phonemes, compared to errors of 86~130 ms with EasyAlign. In addition to this, EasyAlign failed to detect 7% of phonemes, while also inserting 58 spurious phones into the transcription. Future research includes verifying these results for other genres and other Chibchan languages. Finally, these results provide additional evidence for the applicability of natural language processing methods to Chibchan languages and point to future work such as the construction of corpora and the training of automated speech recognition systems.  Spanish Abstract: El alineamiento forzado provee un ahorro drástico de tiempo al alinear grabaciones del habla, y es útil para el estudio de las lenguas indígenas, las cuales cuentan con pocos recursos para generar corpus y modelos computacionales. Aquí comparamos dos sistemas de alineamiento, FAVE-align e EasyAlign, para determinar cuál provee mayor precisión al alinear habla en la lengua chibcha bribri. Alineamos una narración y comparamos el error al tratar de encontrar el centro de las palabras y los bordes de los fonemas con sus equivalentes en una corrección manual. FAVE-align tuvo mejor rendimiento, con un error de 7% comparado con 24% de EasyAlign para el centro de las palabras, y con errores de 22~24 ms para el borde de los fonemas, comparado con 86~130 ms con EasyAlign. Además, EasyAlign no pudo detectar el 7% de los fonemas, y al mismo tiempo añadió 58 sonidos espurios a la transcripción. Como trabajo futuro verificaremos estos resultados con otros géneros hablados y con otras lenguas chibchas. Finalmente, estos resultados comprueban la aplicabilidad de los métodos de procesamiento de lengua natural a las lenguas chibchas, y apuntan a trabajo futuro en la construcción de corpus y el entrenamiento de sistemas de reconocimiento automático del habla.

scholarly journals Análise de discursos em notícias sobre homofobia, racismo e sexismo em comentários de portais brasileiros de notícias

2021 ◽  
Author(s):  
Lucas Rodrigues ◽  
Antonio Jacob Junior ◽  
Fábio Lobato
Keyword(s):  
Social Media ◽  
Natural Language Processing ◽  
Sentiment Analysis ◽  
Data Visualization ◽  
Language Processing ◽  
Topic Modeling ◽  
Hate Speech ◽  
Psychological Impact ◽  
Internet Service ◽  
General Law

Posts with defamatory content or hate speech are constantly foundon social media. The results for readers are numerous, not restrictedonly to the psychological impact, but also to the growth of thissocial phenomenon. With the General Law on the Protection ofPersonal Data and the Marco Civil da Internet, service providersbecame responsible for the content in their platforms. Consideringthe importance of this issue, this paper aims to analyze the contentpublished (news and comments) on the G1 News Portal with techniquesbased on data visualization and Natural Language Processing,such as sentiment analysis and topic modeling. The results showthat even with most of the comments being neutral or negative andclassified or not as hate speech, the majority of them were acceptedby the users.

scholarly journals Weakly Supervised Domain Detection

2019 ◽  
Vol 7 ◽  
pp. 581-596
Author(s):  
Yumo Xu ◽  
Mirella Lapata
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Text Classification ◽  
Multiple Instance Learning ◽  
Text Summarization ◽  
Multilabel Classification ◽  
Processing Task ◽  
Weakly Supervised ◽  
Natural Language Processing Task

In this paper we introduce domain detection as a new natural language processing task. We argue that the ability to detect textual segments that are domain-heavy (i.e., sentences or phrases that are representative of and provide evidence for a given domain) could enhance the robustness and portability of various text classification applications. We propose an encoder-detector framework for domain detection and bootstrap classifiers with multiple instance learning. The model is hierarchically organized and suited to multilabel classification. We demonstrate that despite learning with minimal supervision, our model can be applied to text spans of different granularities, languages, and genres. We also showcase the potential of domain detection for text summarization.

Sign in / Sign up

Export Citation Format

Share Document