Chattack: A Gamified Crowd-Sourcing Platform for Tagging Deceptive & Abusive Behaviour

To read the full-text of this research, you can request a copy directly from the authors.


With the explosion of social networks, the web has been transformed into an arena of inappropriate interactions and content, such as fake news and misinformation, deception, hate speech, inauthentic online behaviour, proselytism, slander, and mobbing. In this demo we present Chattack, a first step towards our aim of providing publicly available datasets for accelerating research in the area of safer online conversations. Chattack is a crowd-sourcing web platform that allows the creation of textual dialogues containing inappropriate interactions or language. To make the platform sustainable and collect as many qualitative dialogues as possible, we build upon a gamified approach that can engage users and provide incentives for the completion of various tasks. We provide the details of our approach, present the functionality of the platform, stress its novel features, and discuss some preliminary results and the lessons learned. The platform is publicly available and we invite the participation of the community for its growth.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
Conference Paper
Full-text available
Gamification has been applied to many linguistic annotation tasks, as an alternative to crowdsourcing platforms to collect annotated data in an inexpensive way. However, we think that still much has to be explored. Games with a Purpose (GWAPs) tend to lack important elements that we commonly see in commercial games, such as 2D and 3D worlds or a story. Making GWAPs more similar to full-fledged video games in order to involve users more easily and increase dissemination is a demanding yet interesting ground to explore. In this paper we present a 3D role-playing game for abusive language annotation that is currently under development.
Full-text available
Background Evidence suggests social media use is associated with mental health in young people but underlying processes are not well understood. This paper i) assesses whether social media use is associated with adolescents' depressive symptoms, and ii) investigates multiple potential explanatory pathways via online harassment, sleep, self-esteem and body image. Methods We used population based data from the UK Millennium Cohort Study on 10,904 14 year olds. Multivariate regression and path models were used to examine associations between social media use and depressive symptoms. Findings The magnitude of association between social media use and depressive symptoms was larger for girls than for boys. Compared with 1–3 h of daily use: 3 to < 5 h 26% increase in scores vs 21%; ≥ 5 h 50% vs 35% for girls and boys respectively. Greater social media use related to online harassment, poor sleep, low self-esteem and poor body image; in turn these related to higher depressive symptom scores. Multiple potential intervening pathways were apparent, for example: greater hours social media use related to body weight dissatisfaction (≥ 5 h 31% more likely to be dissatisfied), which in turn linked to depressive symptom scores directly (body dissatisfaction 15% higher depressive symptom scores) and indirectly via self-esteem. Interpretation Our findings highlight the potential pitfalls of lengthy social media use for young people's mental health. Findings are highly relevant for the development of guidelines for the safe use of social media and calls on industry to more tightly regulate hours of social media use. Funding Economic and Social Research Council.
Conference Paper
Full-text available
Hatebusters is a web application for actively reporting YouTube hate speech, aiming to establish an online community of volunteer citizens. Hatebusters searches YouTube for videos with potentially hateful comments, scores their comments with a classifier trained on human-annotated data and presents users those comments with the highest probability of being hate speech. It also employs gamification elements, such as achievements and leaderboards, to drive user engagement.
Background: Cyberbullying has received wide media attention and appears to be linked to frequent adverse consequences, with multiple suicides reported. This study examined the prevalence of cyberbullying among adolescent psychiatric inpatients and related it to social media usage, current levels of symptoms, and histories of adverse early life experience. Methods: Data on the prevalence of social media utilization and cyberbullying victimization were collected from adolescent psychiatric inpatients aged 13 to 17 years from September 2016 to April 2017. Fifty adolescent psychiatric inpatients completed 2 surveys assessing childhood trauma (the Trauma Symptom Checklist for Children and the Childhood Trauma Questionnaire) and the Cyberbullying Questionnaire. Results: Twenty percent of participants (10/50) had been victimized by cyberbullying. Access to and engagement in social media or Internet-based communication was extremely common, with most participants engaging on a daily basis or more frequently in at least 1 social media activity. Those who had been bullied endorsed significantly higher scores on posttraumatic stress disorder (PTSD), depression, anger, and fantasy dissociation scales than those who were not bullied (all P values < .05). Subjects who reported having been victims of cyberbullying endorsed significantly higher levels of lifetime emotional abuse on the Childhood Trauma Questionnaire than those who were not bullied (P = .013); however, they did not report a significantly higher level of the other types of trauma (physical abuse, sexual abuse, emotional neglect, or physical neglect). More bullied than nonbullied subjects had clinically and statisticallysignificant elevations in hyperresponse, PTSD, and depression scale scores (P < .05). Conclusions: Being cyberbullied was associated with greater psychiatric symptom severity. Further, histories of emotional abuse were correlated with recent cyberbullying. These data suggest that individuals with histories of childhood trauma also seem vulnerable to continued adverse experiences during adolescence.
Gamification platform for collecting task-oriented dialogue data
  • O Haruna
  • N Hitoshi
  • T Takenobu
  • Y Hikaru
How much online abuse is there
  • A H B Vidgen
  • H Margetts