Identifying Right-Wing Extremism in German Twitter Profiles: A Classification Approach

Hartung, Matthias; Klinger, Roman; Schmidtke, Franziska; Vogel, Lars

doi:10.1007/978-3-319-59569-6_40

Cited by 17 publications

(17 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To conduct experiments, we used different classifiers for the following three feature representation techniques in the baselines [7,8,12]: (i) n-gram It is the state-of-theart technique [12]) (ii) bag-of-words The bag-of-word, also called Count vectorizer technique, makes use of word frequency [7,13], and (iii) TF-IDF A feature vector is created for text classification [8].…”

Section: Baseline Methodsmentioning

confidence: 99%

“…Researchers have also begun to investigate various ways of automatically analyzing extremist affiliations in languages other than English. In this connection, Hartung et al [13] proposed a machine learning technique for detecting extremist posts in German Twitter accounts. Different features are experimented, such as emotions, linguistic patterns, and textual clues.…”

Section: Related Workmentioning

confidence: 99%

“…The feature set for such classifiers is encoded by taskdriven embedding trained over different classifiers: CNN, LSTM, and CNN + LSTM. As baselines, we compare with feature set which consists of n-grams [12], TF-DF, and bag of words (BoW) [13].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Detection and classification of social media-based extremist affiliations using sentiment analysis techniques

Ahmad

Asghar

Alotaibi

et al. 2019

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

With the tremendous increase in the use of social network sites like Twitter and Facebook, online community is exchanging information in the form of opinions, sentiments, emotions, and intentions, which reflect their affiliations and aptitude towards an entity, event and policy [1-3]. The propagation of extremist content has also been increasing and being considered as a serious issue in the recent era due to the rise of militant groups such as Irish Republican Army, Revolutionary Armed Forces of Colombia (FARC), Al Quaeda, ISIS (Daesh), Al Shabaab, Taliban, Hezbollah and others [4]. These groups have spread their roots not only at the community levels but also their networks are gaining control of social networking sites [5]. These networking sites are vulnerable and approachable platforms for the group strengthening, propaganda, brainwashing, and fundraising due to its massive impact on public sentiments and opinions. Opinions expressed on such sites give an important clue about the activities and behavior of online users. Detection of such extremist content is important to analyze user sentiment towards some extremist group and to discourage such associated unlawful acts. It is also beneficial in terms of classifying user's extremist affiliation by filtering tweets prior to their onward transmission, recommendation or training AI Chatbot from tweets [6].

show abstract

Section: Baseline Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Detection and classification of social media-based extremist affiliations using sentiment analysis techniques

Ahmad

Asghar

Alotaibi

et al. 2019

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…In very recent work, Wei and Singh (2017) present an approach to detecting Jihadism on Twitter both at the level of user profiles and individual Tweets, using a graph-based approach. The only approach towards automated detection of right-wing extremist users on Twitter we are aware of is our previous work (Hartung et al, 2017).…”

Section: Background and Related Workmentioning

confidence: 99%

Ranking Right-Wing Extremist Social Media Profiles by Similarity to Democratic and Extremist Groups

Hartung

Klinger

Schmidtke

et al. 2017

Proceedings of the 8th Workshop on Computational Approaches To Subjectivity, Sentiment and Social Media Analysis

Self Cite

View full text Add to dashboard Cite

Social media are used by an increasing number of political actors. A small subset of these is interested in pursuing extremist motives such as mobilization, recruiting or radicalization activities. In order to counteract these trends, online providers and state institutions reinforce their monitoring efforts, mostly relying on manual workflows. We propose a machine learning approach to support manual attempts towards identifying right-wing extremist content in German Twitter profiles. Based on a fine-grained conceptualization of rightwing extremism, we frame the task as ranking each individual profile on a continuum spanning different degrees of right-wing extremism, based on a nearest neighbour approach. A quantitative evaluation reveals that our ranking model yields robust performance (up to 0.81 F 1 score) when being used for predicting discrete class labels. At the same time, the model provides plausible continuous ranking scores for a small sample of borderline cases at the division of right-wing extremism and New Right political movements.

show abstract

“…Development in the field of monitoring extremist content on social networks on the Internet is also quite active [6,7]. In particular, the work "Predicting online extremism, content adopters, and interaction reciprocity" presents a technology for detecting extremist users, for predicting users of extremist content and interaction in social networks [8].…”

Section: Introductionmentioning

confidence: 99%

Development of conceptual model for digital monitoring of extremist attitudes and identification of risk groups in the youth environment

Vicentiy¹,

Popova²,

Eliseev³

2019

Proceedings of the International Scientific and Practical Conference on Digital Economy (ISCDE 2019)

View full text Add to dashboard Cite

The relevance of the study is determined by the growth of international terrorism and extremism in recent decades. With the growing dynamics of social change, it is important to quickly respond to both positive and negative changes. In a postindustrial society, the most important issue is the speed of decision making. Monitoring of important changes in society can partially solve this problem. Monitoring of social attitudes allows to identify risk groups by identifying extremist attitudes to prevent the further spread of extremist ideology among young people in the early stages of its development. In the course of the project implementation, the approved scientific and methodological support and tools for sociological monitoring of extremist attitudes and identification of extremist behavior risk groups among young people will be obtained. This scientific and methodological support and tools will be used for early diagnosis and prevention of extremism. The scientific novelty of the project is to develop a new approach to the prevention of extremism among young people, which, unlike the existing approaches, emphasizes the prevention of the spread of extremism at the early stages of its development. The study has a high scientific and practical significance, as it allows to get ready-to-use scientific and methodological support for the sociological monitoring of extremist attitudes among young people for political decision-making processes in the field of improving youth and anti-extremist policies. The paper describes the result of developing a conceptual model of digital monitoring of extremist attitudes and identifying risk groups in the youth environment. A conceptual model can be represented in the form of a scheme that includes four interconnected modules: a theoretical and methodological module, a methodical module, an empirical module, and an analytical module. Four stages of monitoring are described, and the main activities at each stage and their main results are highlighted. The basic elements that constitute the scientific and methodological support of sociological monitoring of extremist attitudes and the identification of risk groups in the youth environment are described. Expected results of the study are formulated and substantiation of their scientific significance in theoretical and applied terms is given.

show abstract

Identifying Right-Wing Extremism in German Twitter Profiles: A Classification Approach

Cited by 17 publications

References 10 publications

Detection and classification of social media-based extremist affiliations using sentiment analysis techniques

Detection and classification of social media-based extremist affiliations using sentiment analysis techniques

Ranking Right-Wing Extremist Social Media Profiles by Similarity to Democratic and Extremist Groups

Development of conceptual model for digital monitoring of extremist attitudes and identification of risk groups in the youth environment

Contact Info

Product

Resources

About