One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of predicting from the very start of a conversation whether it will get out of hand. As opposed to detecting undesirable behavior after the fact, this task aims to enable early, actionable prediction at a time when the conversation might still be salvaged.To this end, we develop a framework for capturing pragmatic devices-such as politeness strategies and rhetorical prompts-used to start a conversation, and analyze their relation to its future trajectory. Applying this framework in a controlled setting, we demonstrate the feasibility of detecting early warning signs of antisocial behavior in online discussions. * Corresponding senior author.

We present a corpus that encompasses the complete history of conversations between contributors to Wikipedia, one of the largest online collaborative communities. By recording the intermediate states of conversationsincluding not only comments and replies, but also their modifications, deletions and restorations-this data offers an unprecedented view of online conversation. This level of detail supports new research questions pertaining to the process (and challenges) of large-scale online collaboration. We illustrate the corpus' potential with two case studies that highlight new perspectives on earlier work. First, we explore how a person's conversational behavior depends on how they relate to the discussion's venue. Second, we show that community moderation of toxic behavior happens at a higher rate than previously estimated. Finally the reconstruction framework is designed to be language agnostic, and we show that it can extract high quality conversational data in both Chinese and English.

The wide spread of unfounded election fraud claims surrounding the U.S. 2020 election had resulted in undermining of trust in the election, culminating in violence inside the U.S. capitol. Under these circumstances, it is critical to understand discussions surrounding these claims on Twitter, a major platform where the claims disseminate. To this end, we collected and release the VoterFraud2020 dataset, a multi-modal dataset with 7.6M tweets and 25.6M retweets from 2.6M users related to voter fraud claims. To make this data immediately useful for a wide area of researchers, we further enhance the data with cluster labels computed from the retweet graph, user suspension status, and perceptual hashes of tweeted images. We also include in the dataset aggregated information for all external links and YouTube videos that appear in the tweets. Preliminary analyses of the data show that Twitter's ban actions mostly affected a specific community of voter fraud claim promoters, and exposes the most common URLs, images and YouTube videos shared in the data.

Social media provides a critical communication platform for political figures, but also makes them easy targets for harassment. In this paper, we characterize users who adversarially interact with political figures on Twitter using mixed-method techniques. The analysis is based on a dataset of 400 thousand users' 1.2 million replies to 756 candidates for the U.S. House of Representatives in the two months leading up to the 2018 midterm elections. We show that among moderately active users, adversarial activity is associated with decreased centrality in the social graph and increased attention to candidates from the opposing party. When compared to users who are similarly active, highly adversarial users tend to engage in fewer supportive interactions with their own party's candidates and express negativity in their user profiles. Our results can inform the design of platform moderation mechanisms to support political figures countering online harassment.

The wide spread of unfounded election fraud claims surrounding the U.S. 2020 election had resulted in undermining of trust in the election, culminating in violence inside the U.S. capitol. Under these circumstances, it is critical to understand the discussions surrounding these claims on Twitter, a major platform where the claims were disseminated. To this end, we collected and released the VoterFraud2020 dataset, a multi-modal dataset with 7.6M tweets and 25.6M retweets from 2.6M users related to voter fraud claims. To make this data immediately useful for a diverse set of research projects, we further enhance the data with cluster labels computed from the retweet graph, each user's suspension status, and the perceptual hashes of tweeted images. The dataset also includes aggregate data for all external links and YouTube videos that appear in the tweets. Preliminary analyses of the data show that Twitter's user suspension actions mostly affected a specific community of voter fraud claim promoters, and exposes the most common URLs, images and YouTube videos shared in the data.