Karthik Dinakar

Common Sense Reasoning for Detection, Prevention, and Mitigation of Cyberbullying

Cyberbullying (harassment on social networks) is widely recognized as a serious social problem, especially for adolescents. It is as much a threat to the viability of online social networks for youth today as spam once was to email in the early days of the Internet. Current work to tackle this problem has involved social and psychological studies on its prevalence as well as its negative effects on adolescents. While true solutions rest on teaching youth to have healthy personal relationships, few have considered innovative design of social network software as a tool for mitigating this problem. Mitigating cyberbullying involves two key components: robust techniques for effective detection and reflective user interfaces that encourage users to reflect upon their behavior and their choices. Spam filters have been successful by applying statistical approaches like Bayesian networks and hidden Markov models. They can, like Google’s GMail, aggregate human spam judgments because spam is sent nearly identically to many people. Bullying is more personalized, varied, and contextual. In this work, we present an approach for bullying detection based on state-of-the-art natural language processing and a common sense knowledge base, which permits recognition over a broad spectrum of topics in everyday life. We analyze a more narrow range of particular subject matter associated with bullying (e.g. appearance, intelligence, racial and ethnic slurs, social acceptance, and rejection), and construct BullySpace, a common sense knowledge base that encodes particular knowledge about bullying situations. We then perform joint reasoning with common sense knowledge about a wide range of everyday life topics. We analyze messages using our novel AnalogySpace common sense reasoning technique. We also take into account social network analysis and other factors. We evaluate the model on real-world instances that have been reported by users on Formspring, a social networking website that is popular with teenagers. On the intervention side, we explore a set of reflective user-interaction paradigms with the goal of promoting empathy among social network participants. We propose an “air traffic control”-like dashboard, which alerts moderators to large-scale outbreaks that appear to be escalating or spreading and helps them prioritize the current deluge of user complaints. For potential victims, we provide educational material that informs them about how to cope with the situation, and connects them with emotional support from others. A user evaluation shows that in-context, targeted, and dynamic help during cyberbullying situations fosters end-user reflection that promotes better coping strategies.

Let's Gang Up on Cyberbullying

Cyberbullying has emerged as a major problem in recent years, afflicting both children and young adults. Tragic stories in the news about suicides of bullied teens have drawn public attention to the issue, and statistics indicate that its prevalence is growing. A 2006 survey commissioned by the National Crime Prevention Council showed that more than 43 percent of US teens were subjected to cyberbullying at some point in the previous year (www.ncpc.org/ cyberbullying), while a 2008 survey by UCLA researchers reported that nearly three-quarters of teens had been bullied online at least once in the past 12 months (www.safeinyourspace. org/2008juvonengross.pdf). This paper discuss the novel design of social network software that can help prevent and manage the growing problem of cyberbullying.

Computing in Mental Health

18.5% of adults in the US suffer mental illness. Just under half of all adults will experience mental illness at some point in their life. These compelling statistics have prompted computing researchers and practitioners to work toward developing technologies that can support those with mental illness and promote thriving universally. For example, wearables and sensors can help detect mental states, smartphone apps can be used to expand the reach of interventions, and our understanding of the impacts of everyday technology on our mental health can contribute to a future of technology design for flourishing. This interdisciplinary workshop will provide the opportunity for mental health professionals and technologists to come together to explore how new computing technologies can support mental health and promote psychological flourishing.

How to Cope With Digital Stress

There is considerable interest in ways to support adolescents in their digital lives, particularly related to the relational challenges they face. While researchers have explored coping with cyberbullying, the scope of relevant digital issues is considerably broader. Through the lens of online peer responses to personal accounts posted by adolescents, this study explores recommended strategies for coping with different experiences of socio-digital stress, including both hostility-oriented issues and digital challenges related to navigating close relationships. A content analysis of 628 comments posted in response to 180 stories of digital stress reveals five common recommendations: Get Help from others, Communicate Directly, Cut Ties with the person involved, Ignore the situation, and Utilize Digital Solutions. The most common recommendation for hostility-oriented issues is to Get Help, while Cut Ties is most common for issues that arise in close relationships. Variations in the pattern of recommendations proposed for different digital issues and for each type of recommendation are described. The findings point to both practical implications for supporting digital youth and next steps for research.

Agile development: overcoming a short-term focus in implementing best practices

Agile development deemphasizes long-term planning in favor of short-term adaptiveness. This is a strength in a rapidly changing development environment. However, this short-term focus creates a temptation to neglect best practices that are essential to long-term success. This report outlines my experience as a software developer in a leading internet portal that thrives on agile development using SCRUM. It describes the problems that arose when best practices were ignored and how our team overcame them.

Mixed-Initiative Real-Time Topic Modeling & Visualization for Crisis Counseling

Text-based counseling and support systems have seen an increasing proliferation in the past decade. We present Fathom, a natural language interface to help crisis counselors on Crisis Text Line, a new 911-like crisis hotline that takes calls via text messaging rather than voice. Text messaging opens up the opportunity for software to read the messages as well as people, and to provide assistance for human counselors who give clients emotional and practical support. Crisis counseling is a tough job that requires dealing with emotionally stressed people in possibly life-critical situations, under time constraints. Fathom is a system that provides topic modeling of calls and graphical visualization of topic distributions, updated in real time. We develop a mixed-initiative paradigm to train coherent topic and word distributions and use them to power real-time visualizations aimed at reducing counselor cognitive overload. We believe Fathom to be the first real-time computational framework to assist in crisis counseling.

2nd Symposia on Computing and Mental Health

The World Health Organization predicts that by the year 2030, depression and other mental illnesses will be the leading disease burden globally. The rapid penetration and advancement of mobile phones and technology have given rise to unprecedented opportunities for close collaboration between computation researchers and mental health practitioners. The intersection between wearable computing, design of naturalistic observation experiments and statistical causal inference offers promising avenues for developing technologies to help those in mental distress; yet human factors inquiry and design are often the missing ingredients in this powerful mix. This second inter-disciplinary workshop will provide an opportunity for researchers in mental health, computation and causal inference to come together under the much needed auspices of human-centric design, towards the development and deployment of new technologies mental health technologies and interventions.

BITxBIT: Encouraging Behavior Change with N=2 Experiments

In this work we introduce an experimental methodology and open-sourced web application designed to promote behavior change and wellbeing within a workplace environment. Colleagues are paired together and asked to design a Behavioral Intervention Technology (BIT) uniquely customized to suit their partners behavior change goal. We present the results of a preliminary evaluation of the experiment, and suggest ways to further improve and expand our experiment design.