Related papers: Beyond Trial-and-Error: Predicting User Abandonmen…
Large language models are increasingly used to mediate everyday interpersonal dilemmas, yet how their advisory defaults interact with the concentrated moral orders of specific communities remains poorly understood. This article compares…
Developing a strong community requires empowered leadership capable of overcoming governance challenges. New online platforms have given users opportunities to practice governance through content moderation roles. The over 2.8 million…
Moderators and automated methods enforce bans on malicious users who engage in disruptive behavior. However, malicious users can easily create a new account to evade such bans. Previous research has focused on other forms of online…
Social media algorithms are thought to amplify variation in user beliefs, thus contributing to radicalization. However, quantitative evidence on how algorithms and user preferences jointly shape harmful online engagement is limited. I…
Causal effect moderation investigates how the effect of interventions (or treatments) on outcome variables changes based on observed characteristics of individuals, known as potential effect moderators. With advances in data collection,…
Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…
Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is…
Many works related to Twitter aim at characterizing its users in some way: role on the service (spammers, bots, organizations, etc.), nature of the user (socio-professional category, age, etc.), topics of interest , and others. However, for…
User intended actions are widely seen in many areas. Forecasting these actions and taking proactive measures to optimize business outcome is a crucial step towards sustaining the steady business growth. In this work, we focus on pre-…
The COVID-19 pandemic has escalated mental health crises worldwide, with social isolation and economic instability contributing to a rise in suicidal behavior. Suicide can result from social factors such as shame, abuse, abandonment, and…
Facebook and Twitter recently announced community-based review platforms to address misinformation. We provide an overview of the potential affordances of such community-based approaches to content moderation based on past research and…
Moderation of user-generated content in an online community is a challenge that has great socio-economical ramifications. However, the costs incurred by delegating this work to human agents are high. For this reason, an automatic system…
Polarization, declining trust, and wavering support for democratic norms are pressing threats to U.S. democracy. Exposure to verified and quality news may lower individual susceptibility to these threats and make citizens more resilient to…
Online competitive action games have flourished as a space for entertainment and social connections, yet they face challenges from a small percentage of players engaging in disruptive behaviors. This study delves into the under-explored…
Social media platforms provide valuable opportunities for users to gather information, interact with friends, and enjoy entertainment. However, their addictive potential poses significant challenges, including overuse and negative…
This paper studies the dynamics of opinion formation and polarization in social media. We investigate whether users' stance concerning contentious subjects is influenced by the online discussions they are exposed to and interactions with…
Social media platform design often incorporates explicit signals of positive feedback. Some moderators provide positive feedback with the goal of positive reinforcement, but are often unsure of their ability to actually influence user…
Despite impressive performance in many benchmark datasets, AI models can still make mistakes, especially among out-of-distribution examples. It remains an open question how such imperfect models can be used effectively in collaboration with…
Almost 50% depression patients face the risk of going into relapse. The risk increases to 80% after the second episode of depression. Although, depression detection from social media has attained considerable attention, depression relapse…
Generating models from large data sets -- and determining which subsets of data to mine -- is becoming increasingly automated. However choosing what data to collect in the first place requires human intuition or experience, usually supplied…