Detecting radicalization trajectories using graph pattern matching algorithms

Hung, Benjamin W. K.; Jayasumana, Anura P.; Bandara, Vidarshana W.

doi:10.1109/isi.2016.7745498

Cited by 12 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results are an adjunct to the proposal that radicalization trajectories can be detected using graph pattern matching algorithms to analyze fused data from social media and government/law enforcement agencies (Hung, et al, 2016;, and research that attempts to identify signals for detecting terror threats (Brynielsson, Horndahl, Johansson, Kaati, Mårtenson, & Svenson, 2013). Importantly, our work differs in focus by elucidating the mechanisms of social media interactions and communication that predict within-person change, and thus could further enhance the discriminatory ability of such algorithms.…”

Section: Practical Implicationsmentioning

confidence: 83%

Detecting psychological change through mobilizing interactions and changes in extremist linguistic style

Smith

Wakeford

Cribbin

et al. 2020

Computers in Human Behavior

View full text Add to dashboard Cite

show abstract

Section: Practical Implicationsmentioning

confidence: 83%

Detecting psychological change through mobilizing interactions and changes in extremist linguistic style

Smith

Wakeford

Cribbin

et al. 2020

Computers in Human Behavior

View full text Add to dashboard Cite

show abstract

“…In the online space, interventions could take the form of disseminating narratives and communications, creating alternative group connections, and group discussions that recognize and validate grievance while adding nuance to “all or nothing” ideas for action. Social-media communications data should be triangulated with ground-truth data from government/law enforcement agencies to enhance the discriminatory ability of techniques such as graph pattern-matching algorithms (Hung, Jayasumana, & Bandara, 2016, 2018) and research that identifies signals for detecting terror threats (Brynielsson et al, 2013).…”

Section: Future Directions: the Specificity Problemmentioning

confidence: 99%

The Need to Refocus on the Group as the Site of Radicalization

Smith

Blackwood

Thomas

2019

Perspect Psychol Sci

View full text Add to dashboard Cite

The past decade has witnessed burgeoning efforts among governments to prevent people from developing a commitment to violent extremism (conceived of as a process of radicalization). These interventions acknowledge the importance of group processes yet in practice primarily focus on the idiosyncratic personal vulnerabilities that lead people to engage in violence. This conceptualization is problematic because it disconnects the individual from the group and fails to adequately address the role of group processes in radicalization. To address this shortcoming, we propose a genuinely social psychological account of radicalization as an alternative. We draw on recent developments in theory and research in psychological science to suggest that radicalization is fundamentally a group socialization process through which people develop identification with a set of norms—that may be violent or nonviolent—through situated social interactions that leverage their shared perceptions and experiences. Our alternative provides a way of understanding shifts toward violent extremism that are caused by both the content (focal topics) and process of social interactions. This means that people’s radicalization to violence is inseparable from the social context in which their social interactions take place.

show abstract

“…Pattern matching with text refers to the task of finding a static pattern in a text ( Amir et al, 2007 ). Different variants of pattern matching algorithm have been widely applied to medical text (e.g., Menger et al, 2018 ) and social media text data (e.g., Hung et al, 2016 ). For the purpose of this study, pattern matching method was used to automate and implement the proposed algorithm to the 575 sampled cases.…”

Section: Methodsmentioning

confidence: 99%

Detecting premature departure in online text-based counseling using logic-based pattern matching

Chan

Tsang

et al. 2021

Internet Interventions

View full text Add to dashboard Cite

Background More so than face-to-face counseling, users of online text-based services might drop out from a session before establishing a clear closure or expressing the intention to leave. Such premature departure may be indicative of heightened risk or dissatisfaction with the service or counselor. However, there is no systematic way to identify this understudied phenomenon. Purpose This study has two objectives. First, we developed a set of rules and used logic-based pattern matching techniques to systematically identify premature departures in an online text-based counseling service. Second, we validated the importance of premature departure by examining its association with user satisfaction. We hypothesized that the users who rated the session as less helpful were more likely to have departed prematurely. Method We developed and tested a classification model using a sample of 575 human-annotated sessions from an online text-based counseling platform. We used 80% of the dataset to train and develop the model and 20% of the dataset to evaluate the model performance. We further applied the model to the full dataset (34,821 sessions). We compared user satisfaction between premature departure and completed sessions based on data from a post-session survey. Results The resulting model achieved 97% and 92% F1 score in detecting premature departure cases in the training and test sets, respectively, suggesting it is highly consistent with the judgment of human coders. When applied to the full dataset, the model classified 15,150 (43.5%) sessions as premature departure and the remaining 19,671 (56.5%) as completed sessions. Completed cases (15.2%) were more likely to fill the post-chat survey than premature departure cases (4.0%). Premature departure was significantly associated with lower perceived helpfulness and effectiveness in distress reduction. Conclusions The model is the first that systematically and accurately identifies premature departure in online text-based counseling. It can be readily modified and transferred to other contexts for the purpose of risk mitigation and service evaluation and improvement.

show abstract

Detecting radicalization trajectories using graph pattern matching algorithms

Cited by 12 publications

References 12 publications

Detecting psychological change through mobilizing interactions and changes in extremist linguistic style

Detecting psychological change through mobilizing interactions and changes in extremist linguistic style

The Need to Refocus on the Group as the Site of Radicalization

Detecting premature departure in online text-based counseling using logic-based pattern matching

Contact Info

Product

Resources

About