Detecting Bots to Distinguish Hate Speech on Social Media

Bailurkar, Radhika; Raul, Nataasha

doi:10.1109/icccnt51525.2021.9579883

Cited by 5 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Первый потенциальный сценарий включает в себя широкий или средний охват аудитории при низкой степени персонализации. К таким кампаниям по управлению восприятием относятся самые распространенные сейчас инструменты в виде «бот-ферм», генерирующих необходимую риторику в контексте конкретных событий [Bailurkar, Raul 2021]. В значительной степени целью таких кампаний должно стать смещение эмоционального режима всего общества в сторону большей допустимости ненависти к отдельным явлениям или группам.…”

Section: сценарный анализ социального воздействия риторики ненависти ...unclassified

Political Implications of Hate Speech Digitalization in a Post-Truth Era: Impact on Emotional Regimes in Digital Conflicts

Kolotaev

2022

Vestn. Ross. univ. družby nar., Ser. Politol.

View full text Add to dashboard Cite

The digitalization of public life modifies old phenomena. Some of these changes prove to be detrimental to certain public spheres, including politics. Digital hate speech is one of the most obvious examples of digitalization’s impact on political processes. The manifestation of hatred online became an urgent challenge to political systems globally. In this respect, a theoretical and practical elaboration is necessary to counter the new threat. This study aims to identify the social mechanisms that make hate speech an instrument in information campaigns. The article illustrates the discursive and emotional aspects of the public manifestation of hatred. The theoretical basis of this work is the theory of “emotional regimes” and the concept of “regimes of truth”, which express the mutual influence of subjectivity and public discourse. Comparing the theoretical framework with the practical aspects of hate speech demonstrates that digital platforms and social networks form an environment that accelerates and facilitates the dissemination of hatred in the public space. As a result, various forms of hatred are accepted as a new social norm, which leads to such phenomena as harassment, humiliation, or even physical persecution. The modern technical reality allows to instrumentalize hate speech for manipulation, which results in three main scenarios for social impact: 1) large impact with low personalization; 2) targeted impact with high personalization; 3) broad and decentralized targeted impact using artificial intelligence. While countering each of these scenarios, a key challenge is to combine long-term and specialized measures.

show abstract

Section: сценарный анализ социального воздействия риторики ненависти ...unclassified

Political Implications of Hate Speech Digitalization in a Post-Truth Era: Impact on Emotional Regimes in Digital Conflicts

Kolotaev

2022

Vestn. Ross. univ. družby nar., Ser. Politol.

View full text Add to dashboard Cite

show abstract

“…Additionally, spam links and comments may contain harmful information that can be exploited to distribute malware or phishing scams. It also may contain hate speech that might increase racial problems in society [5].…”

Section: Introductionmentioning

confidence: 99%

Arabic Tweets Spam Detection Based on Various Supervised Machine Learning and Deep Learning Classifiers

Hassan

Elrefaei

Andraws

2023

MSA Engineering Journal

View full text Add to dashboard Cite

In this paper, different machine learning algorithms, ensemble algorithms, and deep learning algorithms are applied to Arabic tweets to detect whether it human-generated or not. The tweets are used twice as preprocessed and nonpreprocessed to measure the effectiveness of Arabic preprocessing in the classification process. The data is also tokenized with various methods like unigram, trigram, and Term Frequency-Inverse Document Frequency. The experiments show that the support vector machine with the non-preprocessed tweets and unigram tokenization has the best performance of 83.11% and a precision of 0.9516 while it predicts the spam or not in a relatively small time.

show abstract

“…Twitter had a global audience of over 368 million monthly active users as of December 2022 which is expected to grow by the next decade [2]. The extensive use of twitter, has led to an increase in the utilization of robotic account as twitter bots [3], where 9 to 15 percentage active twitter account are socialbots, created for various purpose, which often perceived malicious objective [4], Spreading Fake News [5], manipulating the stock market [6], promoting terrorism [7], spreading sexually explicit material [8], and the interference in 2016 United State presidential election [9] are Socialbots, which compromise the authenticity of trends, undermine democracy, and cause harm.…”

Section: Introductionmentioning

confidence: 99%

Towards a Comprehensive Approach for Socialbot Detection on Twitter: Integrating Multiple Features

Owais

Shoaib

Waseem

2023

Preprint

View full text Add to dashboard Cite

The increasing use of social media platforms has brought about various opportunities for people to communicate, share opinions, and express themselves online. However, this has also led to the emergence of socialbots, programmed accounts that mimic human behavior and have the potential to spread fake news, manipulate the stock market, promote terrorism, and interfere in democratic processes. In order to address this problem, various techniques have been employed for socialbots detection, including profile-based, temporal-based, content-based, behavioral-based, and network-based approaches. However, none of these methods have utilized a hybrid of all these features. In this paper, we propose a hybrid approach that integrates all these features to train a model for socialbots detection on Twitter. we use the Twibot-22 dataset for our experiments and evaluate the performance of our proposed approach against benchmark models. With an accuracy of 0.898, the XGBoost model surpassed the benchmark models. This study contributes to the ongoing efforts to maintain the integrity of tweet contents and address the potential harms caused by socialbots on social networks

show abstract

Detecting Bots to Distinguish Hate Speech on Social Media

Cited by 5 publications

References 10 publications

Political Implications of Hate Speech Digitalization in a Post-Truth Era: Impact on Emotional Regimes in Digital Conflicts

Political Implications of Hate Speech Digitalization in a Post-Truth Era: Impact on Emotional Regimes in Digital Conflicts

Arabic Tweets Spam Detection Based on Various Supervised Machine Learning and Deep Learning Classifiers

Towards a Comprehensive Approach for Socialbot Detection on Twitter: Integrating Multiple Features

Contact Info

Product

Resources

About