What are Cyber Social Threats

The role of online platforms as a prime, daily communication tool is coincident with a sharp rise in its misuse, threatening our society in large. These platforms have been implicated for promoting hate speech, radicalization, harassment, cyberbullying, fake news, human trafficking, drug dealing, gender-based stereotyping and violence among other ills, with a significant impact on individual and community well-being. Such content and behaviors are inherently multi-faceted, making the recognition of their narratives challenging for researchers as well as social media companies. The implications to individuals and communities require reliable models and algorithms for detecting, understanding and countering the malevolent behavior in such communications. These challenges have led to a rising prominence of analysis of online communications in academia, politics, homeland security, and industry using computational techniques from natural language processing, statistics, network science, data mining, machine learning, computational linguistics, human-computer interaction, and cognitive science. To meet these challenges, this workshop aims to stimulate research on social, cultural, emotional, communicative, and linguistic aspects of harmful conversations on online platforms and developing novel approaches to analyze, interpret and understand them.

The workshop welcomes for consideration papers that employ quantitative and/or qualitative, analytical, theoretical approaches examining a diverse range of issues related to online harmful communications. Papers on resources/data and tools will also be welcome either for demos or for short/regular talks.

Important Note

The CySoc workshop will be held as a virtual meeting on June 7, 2021. You can find more information on the ICWSM website. You can find the full program and registration information here.

Why attend the CySoc Workshop?

This workshop will bring together researchers and practitioners in computer and social sciences from both academia and industry to exchange ideas on understanding the multi-faceted aspects of harmful content while leading the discussion on building novel computational methods to reliably detect, derive meaning, interpret, understand and counter them. The participants will find opportunities to present and hear about other fundamental research and emerging applications, to exchange ideas and experiences, and to identify new opportunities for collaborations across disciplines. The researchers and practitioners from various disciplines are strongly encouraged to attend, including (but not limited to) behavioral science, computer and information sciences, psychology, sociology, political science, cognitive science, cultural study, information systems, terrorism and counter-terrorism, operations research, and communication.

Themes & Topics

We are interested in both computing and social science approaches that study the above research directions, based on quantitative, qualitative and mixed research methods. We expect to receive submissions and lead discussions on the topics of novel analytic methods, tools, and datasets.


The CySoc workshop has three main themes:

  • Detection and prediction of content, users, and communities
  • Countering harmful narratives
  • Ethical considerations and handling bias


Topics for research and discussions on challenges in dealing with the online harmful content include (but not limited to):

  • Online extremism
  • Harassment and cyberbullying
  • Hate speech
  • Gender-based violence
  • Human trafficking
  • Illicit drug trafficking
  • Mental health implications of social media
  • Ethical considerations on privacy-preserving social media analytics
  • Emotional and psychological support
  • Trust relationship and community dynamics
  • Relationship of the social web and mainstream news media
  • Cultural implications of social web usage
  • Influencer identification and community detection for movements
  • Misinformation and disinformation (e.g., epidemics of fake news, images and videos, during a disaster, health issues and elections)

Important Dates

Paper submissions due: March 27, 2021 April 8, 2021 (Anywhere on Earth)
Final decision notification: April 30, 2021
Camera-ready submissions due: May 7, 2021

Submission Instructions

We invite research papers (8 pages), position and short papers (4 pages), and demo papers (2 pages). Submissions must be original and should not have been published previously or be under consideration for publication while being evaluated for this workshop. Submissions will be evaluated by the program committee based on the quality of the work and its fit to the workshop themes. All submissions should be double-blind and a high-resolution PDF of the paper should be uploaded to the EasyChair submission site before the paper submission deadline. The accepted papers will be presented at the CySoc workshop integrated with the conference, and they will be published as Proceedings of the ICWSM Workshops. All must be submitted, and formatted in AAAI two-column, camera-ready style.

Workshop Program

All times below are in Eastern Time

8.30 – 8.45 AM – Welcome to the CySoc 2021 workshop attendees.
8.45 – 9.45 AM – Keynote I: Brooke Foucault Welles, Northeastern University.

"The Battle for #Baltimore: Networked Counterpublics and the Contested Framing of Urban Unrest".
A growing body of research suggests that Twitter has become a key resource for networked counterpublics to intervene in popular discourse about racism and policing in the United States. At the same time, claims that online communication necessarily results in polarized echo chambers are common. In response to these seemingly contrary impulses in communication research, we explore how the contested online network comprised of tweets about the April 2015 protests in Baltimore, Maryland, evolved as users constructed meaning and debated questions of protest and race. We find that even within this highly polarized debate, counterpublic frames found widespread support on Twitter. Progressive racial justice messages were advanced, in part, by brokers who worked across polarized subcommunities in the network to build mutual understanding and model effective strategies for reconciling disparate accounts of protest events.

9.45 – 10.30 AM – Paper Session I: Three papers will be presented with 15 minutes allocated for each, including Q/A.
10.30 – 10.50 AM – Coffee Break.
10.50 AM – 12.00 PM – Panel Discussion: Fil Menczer (Indiana University), Joan Donovan (Harvard University), Alexandra Olteanu (Microsoft Research).

"The Role of AI in Countering Cyber Social Threats."
Moderated by Aleszu Bajak (USA Today)

12.00 – 12.30 PM – Paper Session II: Two papers will be presented with 15 minutes allocated for each, including Q/A.
12.30 – 1.00 PM - Break.
1.00 – 2.00 PM – Keynote II: Huan Liu, Arizona State University.

"Next Frontiers of Combating Cyber Social Threats".
Cyber social threats can wreak havoc in our lives at various levels. Disinformation and cyberbullying are two such examples. When more people and younger generations spend more time on social media, users are exposed to this new type of social threats. For example, false information is shown that it spreads faster, deeper, and longer on social media. Furthermore, false information is dividing people, polarizing groups, confusing readers, and can be weaponized by nation-states to exert their influence. Cyberbullying happens and inflicts harm often to younger users, resulting in dire consequences for the victims. We have witnessed significant research progress in recent years on disinformation detection and cyberbullying identification. After showing some encouraging development in these difficult tasks of detection and identification, we discuss some questions regarding what’s next beyond detection for building a healthier and less dividing ecosystem on social media in combating cyber social threats.

2.00 – 3.00 PM – Demo presentations: Two demos will be presented with 30 minutes allocated for each, including Q/A.
  • Welton Chang, Eric Curwin: ”Extremist Explorer – A System for Researching Online Violent Hate Speech”.
    Over the last year, Human Rights First has built a system for collecting, identifying, and researching violent hate speech across social media, forums, and chat rooms online. The system is currently used by 50+ researchers and NGOs that investigate online extremism. We will discuss the origins of the system, conduct a demo and talk a bit about the future of the platform.
  • Matthew DeVerna: ”CoVaxxy: Visualizing the relationship between COVID-19 vaccine adoption and online (mis)information”.
    In this demonstration, we will introduce CoVaxxy, a web-based dashboard for visualizing the relationship between COVID-19 vaccine adoption and online (mis)information built by the Observatory on Social Media. Using the growing data set that powers the dashboard, we will also present preliminary results from a deeper investigation into the relationship between vaccine uptake/hesitancy and misinformation in U.S. states and counties.
3.00 – 3.30 PM – Paper Session III: Two papers will be presented with 15 minutes allocated for each, including Q/A.
3.30 – 3.45 PM – Coffee Break.
3.45 – 5.00 PM – Synthesis/Brainstorming exercise 30-minute, resulting in paper concepts for impactful future research, followed by a 40-minute discussion session. The synthesis part will be in zoom break-out rooms, and the discussion will be in the main room.
5.00 – 5.15 PM - Closing Remarks.


Ugur Kursuncu

AI Institute, University of South Carolina, SC, USA

Contact Email

Yelena Mejova

ISI Foundation, Turin, Italy

Contact Email

Megan Squire

Elon University, NC, USA

Contact Email

Jeremy Blackburn

State University of New York at Binghamton, NY, USA

Contact Email

Amit Sheth

AI Institute, University of South Carolina, SC, USA

Contact Email

Program Committee