Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Project Motivation and Research Objectives
Materials and Methods
Data Collection
Data Format
Data Analysis
Project Analysis and Usability Evaluation
Results
Analysis and Usability Evaluation Results
Discussion
References
All Topics
Computer Science
Natural Language Processing

A Web Interface for Analyzing Hate Speech

Profile image of Charalampos DimoulasCharalampos Dimoulas

Future Internet

https://doi.org/10.3390/FI13030080
visibility

…

description

18 pages

link

1 file

Abstract

Social media services make it possible for an increasing number of people to express their opinion publicly. In this context, large amounts of hateful comments are published daily. The PHARM project aims at monitoring and modeling hate speech against refugees and migrants in Greece, Italy, and Spain. In this direction, a web interface for the creation and the query of a multi-source database containing hate speech-related content is implemented and evaluated. The selected sources include Twitter, YouTube, and Facebook comments and posts, as well as comments and articles from a selected list of websites. The interface allows users to search in the existing database, scrape social media using keywords, annotate records through a dedicated platform and contribute new content to the database. Furthermore, the functionality for hate speech detection and sentiment analysis of texts is provided, making use of novel methods and machine learning models. The interface can be accessed online w...

Related papers

Social Media based Hate Speech Detection using Machine Learning
Dr. Nisha Auti, Shreeraj Ghadge, Rajdatta Jadhav, Prajwal Jagtap, Sumit Ranaware, International Journal of Scientific Research in Computer Science, Engineering and Information Technology IJSRCSEIT

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2022

Hate speech is a crime that has been increasing in recent years, not only in person but also online. There are several causes for this. There is tremendous growth in social media that promotes full freedom of expression through anonymity features. Freedom of expression is a human right, but hate speech directed at individuals or groups on the basis of race, caste, religion, ethnicity or nationality, gender, disability, gender identity, etc. is a violation of that sovereignty. Freedom of expression is a human right, but hate speech directed at individuals or groups on the basis of race, caste, religion, ethnicity or nationality, gender, disability, gender identity, etc. is a violation of that sovereignty. It promotes violence and hate crimes, creates social imbalances, and undermines peace, trust and human rights. Revealing hate speech in social media discourse is a very important but complex task. On the one hand, the anonymity provided by the Internet, especially social networks, makes people more likely to engage in hostile behavior. On the other hand, the desire to express one's thoughts on the Internet has increased, leading to the spread of hate speech. Governments and social media platforms can benefit from detection and prevention technologies, as this kind of bigoted language can wreak havoc on society. We help resolve this dilemma by providing a systematic overview of research on this topic in this survey. This project aims to accurately predict various forms by addressing different categories of hate individually and examining a set of text mining functions. Hate speech detection

View PDFchevron_right
“Contro L’Odio”: A Platform for Detecting, Monitoring and Visualizing Hate Speech against Immigrants in Italian Social Media
Manuela Sanguinetti

Italian Journal of Computational Linguistics

The paper describes the Web platform built within the project "Contro l'Odio", for monitoring and contrasting discrimination and hate speech against immigrants in Italy. It applies a combination of computational linguistics techniques for hate speech detection and data visualization tools on data drawn from Twitter. It allows users to access a huge amount of information through interactive maps, also tuning their view, e.g. visualizing the most viral tweets and interactively reducing the inherent complexity of data. Educational courses for high school students have been developed which are centered on the platform and focused on the deconstruction of negative stereotypes against immigrants, Rom and religious minorities, and on the creation of positive narratives. The data collected and analyzed by the platform are also currently used for benchmarking activities within an evaluation campaign, and for paving the way to new projects against hate.

View PDFchevron_right
Computational Linguistics Against Hate: Hate Speech Detection and Visualization on Social Media in the "Contro L'Odio" Project
marco stranisci

The paper describes the Web platform built within the project "Contro l'odio", for monitoring and contrasting discrimination and hate speech against immigrants in Italy. It applies a combination of computational linguistics techniques for hate speech detection and data visualization tools on data drawn from Twitter. It allows users to access a huge amount of information through interactive maps, also tuning their view, e.g., visualizing the most viral tweets and interactively reducing the inherent complexity of data. Educational courses for high school students and citizenship has been developed which are centered on the platform and focused on the deconstruction of negative stereotypes against immigrants, Roma, and religious minorities, and on the creation of positive narratives.

View PDFchevron_right
The Datafication of Hate: Expectations and Challenges in Automated Hate Speech Monitoring
Reeta Pöyhtäri

Frontiers in Big Data, 2020

View PDFchevron_right
Hate Speech Detection in Social Media Surveillance: A Review of Related Literature
INNOVATIVE COMPUTING REVIEW

Innovative Computing Review, 2021

Social media surveillance is a requirement for governments and intelligence agencies around the world to detect and prevent hate crimes. The dynamic and unstructured nature of the textual content available on social media platforms makes it very complex to extract hate related speech patterns from this content. It also creates ambiguities in the data and therefore, data mining techniques become difficult to apply in this scenario. Several alternative techniques were adopted by different researchers in the past to cope with this problem and to capture and analyze such unstructured text for the purpose of hate speech detection. In this paper, we reviewed, categorized and presented a state-of-the-art of these techniques which were divided into three categories namely text mining, sentiment analysis and semantics. The challenges in the application of the existing techniques were also discussed and these can be taken up as future directions.

View PDFchevron_right
Cita en Amores, J. et al. Detecting ideological hatred on Twitter. Development and evaluation of a political ideology hate speech detector in tweets in Spanish. Cuadernos.info, (49), 98-124.
José Octavio Islas Carmona

https://doi.org/10.7764/cdi.49.27817, 2021

AbstrAct | Hate speech spread through social media such as Twitter deserves special attention, as its increase may be related to the rise in hate crimes. Of the 11 categories of discrimination contemplated by the Spanish Ministry of Internal Affairs, the second in which the most hate crimes are registered per year is political ideology. However, this category falls outside of most action plans to study and combat hate crimes. The same occurs in the case of academic works since most focus on analyzing and detecting hate in English and at a general level. The few authors who have targeted their studies to a single type of hate to improve accuracy, have focused on racism, xenophobia, or gender discrimination, but never on political ideology. Furthermore, the detection prototypes developed so far have not used databases generated manually by various coders. This paper aims to overcome these limitations, developing and evaluating an automatic hate speech detector on Twitter in Spanish for reasons of ideological discrimination, using supervised machine learning techniques. For this, we developed a total of eight predictive models from an ad-hoc generated training corpus, and making use of shallow modelling, but also deep learning, which has allowed to improve the final performance of the prototype. In addition, the development of the corpus allowed us to observe that 16.2% of the sample, collected in autumn 2019 and manually analyzed, included some type of ideological hatred. Keywords: hate speech; online hate; Twitter; political ideology; deep learning; machine learning; supervised classification.

View PDFchevron_right
An Italian Twitter Corpus of Hate Speech against Immigrants
marco stranisci

Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018

The paper describes a recently-created Twitter corpus of about 6,000 tweets, annotated for hate speech against immigrants, and developed to be a reference dataset for an automatic system of hate speech monitoring. The annotation scheme was therefore specifically designed to account for the multiplicity of factors that can contribute to the definition of a hate speech notion, and to offer a broader tagset capable of better representing all those factors, which may increase, or rather mitigate, the impact of the message. This resulted in a scheme that includes, besides hate speech, the following categories: aggressiveness, offensiveness, irony, stereotype, and (on an experimental basis) intensity. The paper hereby presented namely focuses on how this annotation scheme was designed and applied to the corpus. In particular, also comparing the annotation produced by CrowdFlower contributors and by expert annotators, we make some remarks about the value of the novel resource as gold standard, which stems from a preliminary qualitative analysis of the annotated data and on future corpus development.

View PDFchevron_right
Tracking Hate in Social Media: Evaluation, Challenges and Approaches
Daksh Patel

SN Computer Science, 2020

This paper presents online hate speech as a societal and computational challenge. Offensive content detection in social media is considered as a multilingual, multi-level, multi-class classification problem for three Indo-European languages. This research problem is offered to the community through the HASOC shared task. HASOC intends to stimulate research and development in hate speech recognition across different languages. Three datasets (in English, German, and Hindi) were developed from Twitter and Facebook, and made available. This paper describes the creation of the multilingual datasets and the annotation method. We will present the numerous approaches based on traditional classifiers, deep neural models, and transfer learning models, along with features used for the classification. Results show that the best classifier for the binary classification might not perform best in the multi-class classification, and the performance of the same classifier varies across the languages. Overall, transfer learning models such as BERT, and deep neural models based on LSTMs and CNNs perform similar but better than traditional classifiers such as SVM. We will conclude the discussion with a list of issues that needs to be addressed for future datasets.

View PDFchevron_right

References (61)

  1. Matsiola, M.; Dimoulas, C.A.; Kalliris, G.; Veglis, A.A. Augmenting User Interaction Experience Through Embedded Multimodal Media Agents in Social Networks. In Information Retrieval and Management; IGI Global: Hershey, PA, USA, 2018; pp. 1972-1993.
  2. Siapera, E.; Veglis, A. The Handbook of Global Online Journalism; John Wiley & Sons: Hoboken, NJ, USA, 2012.
  3. Katsaounidou, A.; Dimoulas, C.; Veglis, A. Cross-Media Authentication and Verification: Emerging Research and Opportunities; IGI Global: Hershey, PA, USA, 2018.
  4. Dimoulas, C.; Veglis, A.; Kalliris, G. Application of mobile cloud based technologies in news reporting: Current trends and future perspectives. In Joel Rodrigues; Lin, K., Lloret, J., Eds.; Mobile Networks and Cloud Computing Convergence for Progressive Services and Applications; IGI Global: Hershey, PA, USA, 2014; Chapter 17; pp. 320-343.
  5. Dimoulas, C.A.; Symeonidis, A.L. Syncing Shared Multimedia through Audiovisual Bimodal Segmentation. IEEE MultiMedia 2015, 22, 26-42. [CrossRef]
  6. Sidiropoulos, E.; Vryzas, N.; Vrysis, L.; Avraam, E.; Dimoulas, C. Growing Media Skills and Know-How in Situ: Technology- Enhanced Practices and Collaborative Support in Mobile News-Reporting. Educ. Sci. 2019, 9, 173. [CrossRef]
  7. Dimoulas, C.A.; Veglis, A.A.; Kalliris, G.; Khosrow-Pour, D.M. Semantically Enhanced Authoring of Shared Media. In Encyclopedia of Information Science and Technology, Fourth Edition; IGI Global: Hershey, PA, USA, 2018; pp. 6476-6487.
  8. Saridou, T.; Veglis, A.; Tsipas, N.; Panagiotidis, K. Towards a semantic-oriented model of participatory journalism management. Available online: https://coming.gr/wp-content/uploads/2020/02/2_2019_JEICOM_SPissue_Saridou_pp.-27-37.pdf (accessed on 18 March 2021).
  9. Cammaerts, B. Radical pluralism and free speech in online public spaces. Int. J. Cult. Stud. 2009, 12, 555-575. [CrossRef]
  10. Fortuna, P.; Nunes, S. A Survey on Automatic Detection of Hate Speech in Text. ACM Comput. Surv. 2018, 51, 1-30. [CrossRef]
  11. Davidson, T.; Warmsley, D.; Macy, M.; Weber, I. Automated hate speech detection and the problem of offensive language. In Proceedings of the International AAAI Conference on Web and Social Media, Palo Alto, CA, USA, 25-28 June 2017.
  12. Ekman, M. Anti-immigration and racist discourse in social media. Eur. J. Commun. 2019, 34, 606-618. [CrossRef]
  13. Burnap, P.; Williams, M.L. Hate speech, machine classification and statistical modelling of information flows on twitter: Interpre- tation and communication for policy decision making. In Proceedings of the 2014 Internet, Policy & Politics Conferences, Oxford, UK, 15-26 September 2014.
  14. Pohjonen, M.; Udupa, S. Extreme speech online: An anthropological critique of hate speech debates. Int. J. Commun. 2017, 11, 1173-1191.
  15. Ben-David, A.; Fernández, A.M. Hate speech and covert discrimination on social media: Monitoring the Facebook pages of extreme-right political parties in Spain. Int. J. Commun. 2016, 10, 1167-1193.
  16. Olteanu, A.; Castillo, C.; Boy, J.; Varshney, K. The effect of extremist violence on hateful speech online. In Proceedings of the twelfth International AAAI Conference on Web and Social Media, Stanford, CA, USA, 25-28 June 2018.
  17. Paz, M.A.; Montero-Díaz, J.; Moreno-Delgado, A. Hate Speech: A Systematized Review. SAGE Open 2020, 10. [CrossRef]
  18. Calvert, C. Hate Speech and Its Harms: A Communication Theory Perspective. J. Commun. 1997, 47, 4-19. [CrossRef]
  19. Boeckmann, R.J.; Turpin-Petrosino, C. Understanding the harm of hate crime. J. Soc. Issues 2002, 58, 207-225. [CrossRef]
  20. Anderson, P. What Is Web 2.0? Ideas, Technologies and Implications for Education; JISC: Bristol, UK, 2007.
  21. Kim, Y.; Lowrey, W. Who are Citizen Journalists in the Social Media Environment? Digit. J. 2014, 3, 298-314. [CrossRef]
  22. Quandt, T. Dark Participation. Media Commun. 2018, 6, 36-48. [CrossRef]
  23. Schmidt, A.; Wiegand, M. A Survey on Hate Speech Detection using Natural Language Processing. In Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, Valencia, Spain, 3 April 2017; pp. 1-10.
  24. Bruns, A. The active audience: Transforming journalism from gatekeeping to gatewatching. In Making Online News: The Ethnography of New Media Production; Paterson, C., Domingo, D., Eds.; Peter Lang: New York, NY, USA, 2008; pp. 171-184.
  25. Gillmor, D. We the media. Grassroots Journalism by the People, for the People; O'Reilly: Sebastopol, CA, USA, 2004.
  26. Hanitzsch, T.; Quandt, T. Online journalism in Germany. In The Handbook of Global Online Journalism; Siapera, E., Veglis, A., Eds.; Wiley-Blackwell: West Sussex, UK, 2012; pp. 429-444.
  27. Singer, J.B.; Hermida, A.; Domingo, D.; Heinonen, A.; Paulussen, S.; Quandt, T.; Reich, Z.; Vujnovic, M. Participatory Journalism. Guarding Open Gates at Online Newspapers; Wiley-Blackwell: Malden, MA, USA, 2018. [CrossRef]
  28. Obermaier, M.; Hofbauer, M.; Reinemann, C. Journalists as targets of hate speech. How German journalists perceive the consequences for themselves and how they cope with it. Stud. Commun. Media 2018, 7, 499-524. [CrossRef]
  29. Boberg, S.; Schatto-Eckrodt, T.; Frischlich, L.; Quandt, T. The Moral Gatekeeper? Moderation and Deletion of User-Generated Content in a Leading News Forum. Media Commun. 2018, 6, 58-69. [CrossRef]
  30. Wolfgang, J.D. Pursuing the Ideal. Digit. J. 2015, 4, 764-783. [CrossRef]
  31. Wintterlin, F.; Schatto-Eckrodt, T.; Frischlich, L.; Boberg, S.; Quandt, T. How to Cope with Dark Participation: Moderation Practices in German Newsrooms. Digit. J. 2020, 8, 904-924. [CrossRef]
  32. Masullo, G.M.; Riedl, M.J.; Huang, Q.E. Engagement Moderation: What Journalists Should Say to Improve Online Discussions. J. Pract. 2020, 1-17. [CrossRef]
  33. Hille, S.; Bakker, P. Engaging the social news user: Comments on news sites and Facebook. J. Pract. 2014, 8, 563-572. [CrossRef]
  34. Wang, S. Moderating Uncivil User Comments by Humans or Machines? The Effects of Moderation Agent on Perceptions of Bias and Credibility in News Content. Digit. J. 2021, 9, 64-83. [CrossRef]
  35. Risch, J.; Krestel, R. Delete or not delete? Semi-automatic comment moderation for the newsroom. In Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying, Santa Fe, NM, USA, 25 August 2018; pp. 166-176.
  36. MacAvaney, S.; Yao, H.-R.; Yang, E.; Russell, K.; Goharian, N.; Frieder, O. Hate speech detection: Challenges and solutions. PLoS ONE 2019, 14, e0221152. [CrossRef]
  37. Ayo, F.E.; Folorunso, O.; Ibharalu, F.T.; Osinuga, I.A. Machine learning techniques for hate speech classification of twitter data: State-of-the-art, future challenges and research directions. Comput. Sci. Rev. 2020, 38, 100311. [CrossRef]
  38. Gitari, N.D.; Zhang, Z.; Damien, H.; Long, J. A Lexicon-based Approach for Hate Speech Detection. Int. J. Multimed. Ubiquitous Eng. 2015, 10, 215-230. [CrossRef]
  39. Arcila-Calderón, C.; de la Vega, G.; Herrero, D.B. Topic Modeling and Characterization of Hate Speech against Immigrants on Twitter around the Emergence of a Far-Right Party in Spain. Soc. Sci. 2020, 9, 188. [CrossRef]
  40. Arcila-Calderón, C.; Herrero, D.B.; Frías, M.; Seoanes, F. Refugees Welcome? Online Hate Speech and Sentiments in Twitter 2 in Spain during the reception of the boat Aquarius. Sustainability 2021, 13, 2728. [CrossRef]
  41. Arcila-Calderón, C.; Blanco-Herrero, D.; Apolo, M.B.V. Rechazo y discurso de odio en Twitter: Análisis de contenido de los tuits sobre migrantes y refugiados en español/Rejection and Hate Speech in Twitter: Content Analysis of Tweets about Migrants and Refugees in Spanish. Rev. Española Investig. Sociol. 2020, 172, 21-40. [CrossRef]
  42. Badjatiya, P.; Gupta, S.; Gupta, M.; Varma, V. Deep Learning for Hate Speech Detection in Tweets. In Proceedings of the 26th International Conference on Compiler Construction, Austin, TX, USA, 5-6 February 2017; pp. 759-760.
  43. Pitsilis, G.K.; Ramampiaro, H.; Langseth, H. Effective hate-speech detection in Twitter data using recurrent neural networks. Appl. Intell. 2018, 48, 4730-4742. [CrossRef]
  44. Ghani, N.A.; Hamid, S.; Hashem, I.A.T.; Ahmed, E. Social media big data analytics: A survey. Comput. Hum. Behav. 2019, 101, 417-428. [CrossRef]
  45. Sánchez-Holgado, P.; Arcila-Calderón, C. Supervised Sentiment Analysis of Science Topics: Developing a Training Set of Tweets in Spanish. J. Infor. Technol. Res. 2020, 13, 80-94. [CrossRef]
  46. Korkmaz, G.; Cadena, J.; Kuhlman, C.J.; Marathe, A.; Vullikanti, A.; Ramakrishnan, N. Multi-source models for civil unrest forecasting. Soc. Netw. Anal. Min. 2016, 6, 1-25. [CrossRef]
  47. Capozzi, A.T.; Lai, M.; Basile, V.; Poletto, F.; Sanguinetti, M.; Bosco, C.; Patti, V.; Ruffo, G.; Musto, C.; Polignano, M.; et al. Computational linguistics against hate: Hate speech detection and visualization on social media in the "Contro L'Odio" project. In Proceedings of the 6th Italian Conference on Computational Linguistics, CLiC-it 2019, Bari, Italy, 13-15 November 2019; Volume 2481, pp. 1-6.
  48. Dimoulas, C.A. Multimedia. In The SAGE International Encyclopedia of Mass Media and Society; Merskin, D.L., Ed.; SAGE Publications, Inc.: Saunders Oaks, CA, USA, 2019.
  49. Dimoulas, C.A. Multimedia Authoring and Management Technologies: Non-Linear Storytelling in the New Digital Media; Association of Greek Academic Libraries: Athens, Greece, 2015; Available online: http://hdl.handle.net/11419/4343 (accessed on 18 March 2021). (In Greek)
  50. Chatzara, E.; Kotsakis, R.; Tsipas, N.; Vrysis, L.; Dimoulas, C. Machine-Assisted Learning in Highly-Interdisciplinary Media Fields: A Multimedia Guide on Modern Art. Educ. Sci. 2019, 9, 198. [CrossRef]
  51. Psomadaki, O.; Dimoulas, C.; Kalliris, G.; Paschalidis, G. Digital storytelling and audience engagement in cultural heritage management: A collaborative model based on the Digital City of Thessaloniki. J. Cult. Herit. 2019, 36, 12-22. [CrossRef]
  52. Katsaounidou, A.; Vrysis, L.; Kotsakis, R.; Dimoulas, C.; Veglis, A. MAthE the Game: A Serious Game for Education and Training in News Verification. Educ. Sci. 2019, 9, 155. [CrossRef]
  53. Graham, M.; Hale, S.A.; Gaffney, D. Where in the World Are You? Geolocation and Language Identification in Twitter. Prof. Geogr. 2014, 66, 568-578. [CrossRef]
  54. De Vries, E.; Schoonvelde, M.; Schumacher, G. No Longer Lost in Translation: Evidence that Google Translate Works for Comparative Bag-of-Words Text Applications. Politi. Anal. 2018, 26, 417-430. [CrossRef]
  55. Loria, S. Textblob Documentation. Available online: https://buildmedia.readthedocs.org/media/pdf/textblob/latest/textblob. pdf (accessed on 18 March 2021).
  56. Clemens, K. Geocoding with openstreetmap data. In Proceedings of the GEOProcessing 2015, Lisbon, Portugal, 22-27 February 2015; p. 10.
  57. Arcila-Calderón, C.; Amores, J.; Blanco, D.; Sánchez, M.; Frías, M. Detecting hate speech against migrants and refugees in Twitter using supervised text classification. In Proceedings of the International Communication Association's 71th Annual Conference, Denver, CO, USA, 27-31 May 2021.
  58. Chollet, F. Keras: The Python Deep Learning Library. Available online: http://ascl.net/1806.022 (accessed on 18 March 2021).
  59. Spiliotopoulou, L.; Damopoulos, D.; Charalabidis, Y.; Maragoudakis, M.; Gritzalis, S. Europe in the shadow of financial crisis: Policy Making via Stance Classification. In Proceedings of the 50th Hawaii International Conference on System Sciences (2017), Hilton Waikoloa Village, HI, USA, 4-7 January 2017.
  60. Thelwall, M.; Buckley, K.; Paltoglou, G.; Cai, D.; Kappas, A. Sentiment strength detection in short informal text. J. Am. Soc. Inf. Sci. Technol. 2010, 61, 2544-2558. [CrossRef]
  61. Nakayama, H.; Kubo, T.; Kamura, J.; Taniguchi, Y.; Liang, X. Doccano: Text Annotation tool for Human. 2018. Available online: https://github.com/doccano/doccano (accessed on 18 March 2021).

Related papers

A Turkish Hate Speech Dataset and Detection System
Aysecan Terzioglu, Reyyan Yeniterzi, Buse Carik (Student), Fatih Beyhan

Language Resources and Evaluation (LREC), 2022

Social media posts containing hate speech are reproduced and redistributed at an accelerated pace, reaching greater audiences at a higher speed. We present a machine learning system for automatic detection of hate speech in Turkish, along with a hate speech dataset consisting of tweets collected in two separate domains. We first adopted a definition for hate speech that is in line with our goals and amenable to easy annotation; then designed the annotation schema for annotating the collected tweets. The Istanbul Convention dataset consists of tweets posted following the withdrawal of Turkey from the Istanbul Convention. The Refugees dataset was created by collecting tweets about immigrants by filtering based on commonly used keywords related to immigrants. Finally, we have developed a hate speech detection system using the transformer architecture (BERTurk), to be used as a baseline for the collected dataset. The binary classification accuracy is 77% when the system is evaluated using 5-fold cross validation on the Istanbul Convention dataset and 71% for the Refugee dataset. We also tested a regression model with 0.66 and 0.83 RMSE on a scale of [0-4], for the Istanbul Convention and Refugees datasets.

View PDFchevron_right
FADOHS: Framework for Detection and Integration of Unstructured Data of Hate Speech on Facebook Using Sentiment and Emotion Analysis
Axel Rodriguez

IEEE Access, 2022

Hate speech is a form of expression that assaults a person or a community based on race, origin, religion, sexual orientation, or other attributes. Although it can be expressed in multiple ways, both online and offline, the increasing popularity of social media has exponentially increased both its use and severity. Therefore, the aim of this research is to locate and analyze the unstructured data of selected social media posts that intend to spread hate in the comment sections. To address this issue, we propose a novel framework called FADOHS, which combines data analysis and natural language processing strategies, to sensitize all social media providers to the pervasiveness of hate on social media. Specifically, we use sentiment and emotion analysis algorithms to analyze recent posts and comments on these pages. Posts suspected of containing dehumanizing words will be processed before fed to the clustering algorithm for further evaluation. According to the experimental results, the proposed FADOHS framework is able to surpass the state-of-the-art approach in terms of precision, recall, and F1 scores by approximately 10%. INDEX TERMS Emotion recognition, clustering algorithm, sentiment analysis, data mining. I. INTRODUCTION Mark Zuckerberg, CEO of Facebook, once commented ''Hate speech and racism do not have a place on Facebook'' [1]. Although Facebook has adopted various artificial intelligence (AI) techniques to prevent hate speech on its platform, some issues persist. For example, as stated by the company when they published statistics on the crackdown on hate speech, ''For hate speech, our technology still does not work well, so it needs to be checked by our review teams. We removed 2.5 million pieces of hate speech in Q1 2018, where 38% of which was flagged by our technology'' [2]. The most persistent question in this pursuit is very difficult to address using AI alone: What is hate speech? This question draws continuous discussion, which brings various definitions of hate speech; for example, ''Hate speech is public The associate editor coordinating the review of this manuscript and approving it for publication was Chien-Ming Chen. expressions which spread, incite, promote or justify hatred, discrimination or hostility toward a specific group'' [3] and ''We define hate speech as a direct attack on people based on what we call protected characteristics-race, ethnicity, national origin, religious affiliation, sexual orientation, caste, sex, gender, gender identity, and serious disease or disability'' [4]. Facebook admitted that the problem comes from the fact that AI is not yet sufficiently advanced to determine whether someone is promoting hate or simply describing an experience [5]. Sara Chinnasamy and Norain Abdul Manaf mentioned that hate speech can also be promoted in subtle ways, such as discussing controversial topics to elicit hate comments [6]. Anat Ben-David and Ariadna Matamoros-Fernandez argued that despite the efforts of Facebook, hate comments abound. The authors remarked that many users express their subliminal hatred through vicious messages or commentaries. These posts, which are not uncovered by Ph.D. degree from the

View PDFchevron_right
Hate Speech Research: Algorithmic and Qualitative Evaluations. A Case Study of Anti-Gypsy Hate on Twitter
Stefano Pasta

Research on Education and Media

Hate speech may be the research focus of the interdisciplinary field of hate studies, but it is also a difficult phenomenon to define. Internationally, there are several detection studies on automatically detecting hate speech. They can be grouped according to two approaches: the first includes searching using only machine learning methods, while the second includes studies that combine automatic searching with human classification. The case study on anti-Gypsy hate in Italian on Twitter in the second half of 2020 falls into the second category, and its methods are outlined here. Based on the results (annotation as ‘hate’/‘non-hate’, identification of forms of rhetoric and anti-Gypsyism), the researchers propose classifying online content according to seven indicators called the ‘spectrum of online hate’.

View PDFchevron_right
Indicators for characterising online hate speech and its automatic detection
Stefano Pasta

arXiv (Cornell University), 2024

We examined four case studies in the context of hate speech on Twitter in Italian from 2019 to 2020, aiming at comparing the classification of the 3,600 tweets made by expert pedagogists with the automatic classification made by machine learning algorithms. Pedagogists used a novel classification scheme based on seven indicators that characterize hate. These indicators are: the content is public, it affects a target group, it contains hate speech in explicit verbal form, it will not redeem, it has intention to harm, it can have a possible violent response, it incites hatred and violence. The case studies refer to Jews, Muslims, Roma, and immigrants target groups. We find that not all the types of hateful content are equally detectable by the machine learning algorithms that we considered. In particular, algorithms perform better in identifying tweets that incite hatred and violence, and those that can have possible violent response.

View PDFchevron_right
AI for Hate Speech Detection in Social Media
Jose Olivas

2020

The main goal of this work focuses on solving the problem of analyzing the data coming from Social Media and exploring the mechanisms for the extraction and representation of knowledge from all the different disciplines outside the world oflnformation Technologies. Soft Computing and Big Data techniques are used to deal with the challenges mentioned. This paper shows a mechanism to detect hate speech in Social Media using Soft Computing and Sentiment Analysis, and it also stablishes the base of a doctoral thesis.

View PDFchevron_right

Related topics

  • Natural Language Processing
  • Sentiment Analysis
  • Future Internet
  • mashine learning
  • news semantics

    • Cited by

    A Prototype Web Application to Support Human-Centered Audiovisual Content Authentication and Crowdsourcing
    Anastasia Katsaounidou

    Future Internet, 2022

    This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

    View PDFchevron_right
    Modeling and Validating a News Recommender Algorithm in a Mainstream Medium-Sized News Organization: An Experimental Approach
    Costas Tziouvas

    Future Internet

    News recommending systems (NRSs) are algorithmic tools that filter incoming streams of information according to the users’ preferences or point them to additional items of interest. In today’s high-choice media environment, attention shifts easily between platforms and news sites and is greatly affected by algorithmic technologies; news personalization is increasingly used by news media to woo and retain users’ attention and loyalty. The present study examines the implementation of a news recommender algorithm in a leading news media organization on the basis of observation of the recommender system’s outputs. Drawing on an experimental design employing the ‘algorithmic audit’ method, and more specifically the ‘collaborative audit’ which entails utilizing users as testers of algorithmic systems, we analyze the composition of the personalized MyNews area in terms of accuracy and user engagement. Premised on the idea of algorithms being black boxes, the study has a two-fold aim: first...

    View PDFchevron_right
    Online Hate Speech and Immigration Acceptance: A Study of Spanish Provinces
    Javier J . Amores

    Social Sciences

    Online hate speech against migrants and refugees poses a grave challenge for coexistence and democracy. However, it also offers an opportunity to measure social acceptance towards this group. Using the Intergroup Contact and the Mediated Intergroup Contact Theory, and an already validated methodology, this article seeks to validate whether the use of hate speech as a predictor of social acceptance is valid at a provincial level in Spain. Contrasting 97,710 tweets about migrants and refugees with secondary data from public Spanish institutions about acceptance of immigration and foreign population, no correlation was observed, rejecting the main hypotheses, and hinting that the application of this approach might not be recommended for smaller entities, such as provinces (NUTS 3). However, the study offers descriptive data about racist hate speech spread on Twitter in Spain, and also discusses the need for more studies using big data to increase knowledge about online hate speech agai...

    View PDFchevron_right
    How to Detect Online Hate towards Migrants and Refugees? Developing and Evaluating a Classifier of Racist and Xenophobic Hate Speech Using Shallow and Deep Learning
    Javier J . Amores

    Sustainability

    Hate speech spreading online is a matter of growing concern since social media allows for its rapid, uncontrolled, and massive dissemination. For this reason, several researchers are already working on the development of prototypes that allow for the detection of cyberhate automatically and on a large scale. However, most of them are developed to detect hate only in English, and very few focus specifically on racism and xenophobia, the category of discrimination in which the most hate crimes are recorded each year. In addition, ad hoc datasets manually generated by several trained coders are rarely used in the development of these prototypes since almost all researchers use already available datasets. The objective of this research is to overcome the limitations of those previous works by developing and evaluating classification models capable of detecting racist and/or xenophobic hate speech being spread online, first in Spanish, and later in Greek and Italian. In the development o...

    View PDFchevron_right
    Theory and Applications of Web 3.0 in the Media Sector
    Andreas Veglis

    Future Internet

    We live in a digital era, with vast technological advancements, which, among others, have a major impact on the media domain. More specifically, progress in the last two decades led to the end-to-end digitalization of the media industry, resulting in a rapidly evolving media landscape. In addition to news digitization, User-Generated Content (UGC) is dominant in this new environment, also fueled by Social Media, which has become commonplace for news publishing, propagation, consumption, and interactions. However, the exponential increase in produced and distributed content, with the multiplied growth in the number of plenary individuals involved in the processes, created urgent needs and challenges that need careful treatment. Hence, intelligent processing and automation incorporated into the Semantic Web vision, also known as Web 3.0, aim at providing sophisticated data documentation, retrieval, and management solutions to meet the demands of the new digital world. Specifically, fo...

    View PDFchevron_right
    580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved