Online social media platforms use automated moderation systems to remove or reduce the visibility of rule-breaking content. While previous work has documented the importance of manual content moderation, the effects of automated content moderation remain largely unknown. Here, in a large study of Facebook comments (n = 412M), we used a fuzzy regression discontinuity design to measure the impact of automated content moderation on subsequent rule-breaking behavior (number of comments hidden/deleted) and engagement (number of additional comments posted). We found that comment deletion decreased subsequent rule-breaking behavior in shorter threads (20 or fewer comments), even among other participants, suggesting that the intervention prevented conversations from derailing. Further, the effect of deletion on the affected user’s subsequent rule-breaking behavior was longer-lived than its effect on reducing commenting in general, suggesting that users were deterred from rule-breaking but not from commenting. In contrast, hiding (rather than deleting) content had small and statistically insignificant effects. Our results suggest that automated content moderation increases adherence to community guidelines.

Social network platforms have enabled large-scale measurement of user-to-user networks such as friendships. Less studied is user sentiment about their networks, such as a user’s satisfaction with their number of friends. We surveyed over 85,000 Facebook users about how satisfied they were with their number of friends on Facebook, connecting these responses to their on-platform activity. As suggested in prior work, we’d expect users who are not satisfied with their friend count to have a higher probability of experiencing the friendship paradox: “your friends have more friends than you”. However in our sample, among users with more than 3,500 friends, no user experiences the friendship paradox. Instead, we still observe that those users with more friends would prefer to have even more friends. The friendship paradox also contributes to local perception bias, defined as the difference between the average number of friends among a user’s friends and the average friend count in the population. Users with a positive perception bias – their friends have more friends than others – are less satisfied with their friend count. We then introduce a weighted perception bias metric that considers the fact that different friends have different effects on an individual’s perception. We find this new weighted perception bias better distinguishes friend count satisfaction outcomes for users with high friend count when compared to the original perception bias metric. We conclude with modeling the behavior interactions via a machine learning model, demonstrating the heterogeneity in the interactions across users with different perception biases. Altogether, these findings offer more insights on users’ friend count satisfaction, which may provide guidelines to improve the user experience and promote healthy interactions.

People compare themselves to one another both offline and online. The specific online activities that worsen social comparison are partly understood, though much existing research relies on people recalling their own online activities post hoc and is situated in only a few countries. To better understand social comparison worldwide and the range of associated behaviors on social media, a survey of 38,000 people from 18 countries was paired with logged activity on Facebook for the prior month. People who reported more frequent social comparison spent more time on Facebook, had more friends, and saw proportionally more social content on the site. They also saw greater amounts of feedback on friends' posts and proportionally more positivity. There was no evidence that social comparison happened more with acquaintances than close friends. One in five respondents recalled recently seeing a post that made them feel worse about themselves but reported conflicting views: half wished they hadn't seen the post, while a third felt very happy for the poster. Design opportunities are discussed, including hiding feedback counts, filters for topics and people, and supporting meaningful interactions, so that when comparisons do occur, people are less affected by them.

Discourse involves two perspectives: a person’s intention in making an utterance and others’ perception of that utterance. The misalignment between these perspectives can lead to undesirable outcomes, such as misunderstandings, low productivity and even overt strife. In this work, we present a computational framework for exploring and comparing both perspectives in online public discussions.

Social comparison is a common focus in discussions of online social media use, and differences in its frequency, causes, and outcomes may arise from country or cultural differences. To understand how these differences play a role in experiences of social comparison on Facebook, a survey of 37,729 people across 18 countries was paired with respondents' activity on Facebook. The findings were augmented with 39 in-person interviews in three countries. Social comparison frequency was more strongly predicted by country than by age, gender, and Facebook activity combined, indicating that country differences are important to consider when studying social comparison. Women's and men's experiences differed greatly between countries. Exposure to high feedback counts on friends' posts was associated with more frequent social comparison, but only in some countries. Design interventions that account for such country differences may be more effective at reducing the negative outcomes of social comparison.

While many people use social network sites to connect with friends and family, some feel that their use is problematic, seriously affecting their sleep, work, or life. Pairing a survey of 20,000 Facebook users measuring perceptions of problematic use with behavioral and demographic data, we examined Facebook activities associated with problematic use as well as the kinds of people most likely to experience it. People who feel their use is problematic are more likely to be younger, male, and going through a major life event such as a breakup. They spend more time on the platform, particularly at night, and spend proportionally more time looking at profiles and less time browsing their News Feeds. They also message their friends more frequently. While they are more likely to respond to notifications, they are also more likely to deactivate their accounts, perhaps in an effort to better manage their time. Further, they are more likely to have seen content about social media or phone addiction. Notably, people reporting problematic use rate the site as more valuable to them, highlighting the complex relationship between technology use and well-being. A better understanding of problematic Facebook use can inform the design of context-appropriate and supportive tools to help people become more in control.

Trust facilitates cooperation and supports positive outcomes in social groups, including member satisfaction, information sharing, and task performance. Extensive prior research has examined individuals' general propensity to trust, as well as the factors that contribute to their trust in specific groups. Here, we build on past work to present a comprehensive framework for predicting trust in groups. By surveying 6,383 Facebook Groups users about their trust attitudes and examining aggregated behavioral and demographic data for these individuals, we show that (1) an individual's propensity to trust is associated with how they trust their groups, (2) smaller, closed, older, more exclusive, or more homogeneous groups are trusted more, and (3) a group's overall friendship-network structure and an individual's position within that structure can also predict trust. Last, we demonstrate how group trust predicts outcomes at both individual and group level such as the formation of new friendship ties.

In online communities, antisocial behavior such as trolling disrupts constructive discussion. While prior work suggests that trolling behavior is confined to a vocal and antisocial minority, we demonstrate that ordinary people can engage in such behavior as well. We propose two primary trigger mechanisms: the individual's mood, and the surrounding context of a discussion (e.g., exposure to prior trolling behavior). Through an experiment simulating an online discussion, we find that both negative mood and seeing troll posts by others significantly increases the probability of a user trolling, and together double this probability. To support and extend these results, we study how these same mechanisms play out in the wild via a data-driven, longitudinal analysis of a large online news discussion community. This analysis reveals temporal mood effects, and explores long range patterns of repeated exposure to trolling. A predictive model of trolling behavior shows that mood and discussion context together can explain trolling behavior better than an individual's history of trolling. These results combine to suggest that ordinary people can, under the right circumstances, behave like trolls.

In online discussion communities, users can interact and share information and opinions on a wide variety of topics. However, some users may create multiple identities, or sockpuppets, and engage in undesired behavior by deceiving others or manipulating discussions. In this work, we study sockpuppetry across nine discussion communities, and show that sockpuppets differ from ordinary users in terms of their posting behavior, linguistic traits, as well as social network structure. Sockpuppets tend to start fewer discussions, write shorter posts, use more personal pronouns such as ``I'', and have more clustered ego-networks. Further, pairs of sockpuppets controlled by the same individual are more likely to interact on the same discussion at the same time than pairs of ordinary users. Our analysis suggests a taxonomy of deceptive behavior in discussion communities. Pairs of sockpuppets can vary in their deceptiveness, i.e., whether they pretend to be different users, or their supportiveness, i.e., if they support arguments of other sockpuppets controlled by the same user. We apply these findings to a series of prediction tasks, notably, to identify whether a pair of accounts belongs to the same underlying user or not. Altogether, this work presents a data-driven view of deception in online discussion communities and paves the way towards the automatic detection of sockpuppets.

Cascades of information-sharing are a primary mechanism by which content reaches its audience on social media, and an active line of research has studied how such cascades, which form as content is reshared from person to person, develop and subside. In this paper, we perform a large-scale analysis of cascades on Facebook over significantly longer time scales, and find that a more complex picture emerges, in which many large cascades recur, exhibiting multiple bursts of popularity with periods of quiescence in between. We characterize recurrence by measuring the time elapsed between bursts, their overlap and proximity in the social network, and the diversity in the demographics of individuals participating in each peak. We discover that content virality, as revealed by its initial popularity, is a main driver of recurrence, with the availability of multiple copies of that content helping to spark new bursts. Still, beyond a certain popularity of content, the rate of recurrence drops as cascades start exhausting the population of interested individuals. We reproduce these observed patterns in a simple model of content recurrence simulated on a real social network. Using only characteristics of a cascade's initial burst, we demonstrate strong performance in predicting whether it will recur in the future.

Crowdsourcing systems lack effective measures of the effort required to complete each task. Without knowing how much time workers need to execute a task well, requesters struggle to accurately structure and price their work. Objective measures of effort could better help workers identify tasks that are worth their time. We propose a data-driven effort metric, ETA (error-time area), that can be used to determine a task's fair price. It empirically models the relationship between time and error rate by manipulating the time that workers have to complete a task. ETA reports the area under the error-time curve as a continuous metric of worker effort. The curve's 10th percentile is also interpretable as the minimum time most workers require to complete the task without error, which can be used to price the task. We validate the ETA metric on ten common crowdsourcing tasks, including tagging, transcription, and search, and find that ETA closely tracks how workers would rank these tasks by effort. We also demonstrate how ETA allows requesters to rapidly iterate on task designs and measure whether the changes improve worker efficiency. Our findings can facilitate the process of designing, pricing, and allocating crowdsourcing tasks.

A large, seemingly overwhelming task can sometimes be transformed into a set of smaller, more manageable microtasks that can each be accomplished independently. For example, it may be hard to subjectively rank a large set of photographs, but easy to sort them in spare moments by making many pairwise comparisons. In crowdsourcing systems, microtasking enables unskilled workers with limited commitment to work together to complete tasks they would not be able to do individually. We explore the costs and benefits of decomposing macrotasks into microtasks for three task categories: arithmetic, sorting, and transcription. We find that breaking these tasks into microtasks results in longer overall task completion times, but higher quality outcomes and a better experience that may be more resilient to interruptions. These results suggest that microtasks can help people complete high quality work in interruption-driven environments.

We present hybrid crowd-machine learning classifiers: classification models that start with a written description of a learning goal, use the crowd to suggest predictive features and label data, and then weigh these features using machine learning to produce models that are accurate and use human-understandable features. These hybrid classifiers enable fast prototyping of machine learning models that can improve on both algorithm performance and human judgment, and accomplish tasks where automated feature extraction is not yet feasible. Flock, an interactive machine learning platform, instantiates this approach. To generate informative features, Flock asks the crowd to compare paired examples, an approach inspired by analogical encoding. The crowd's efforts can be focused on specific subsets of the input space where machine-extracted features are not predictive, or instead used to partition the input space and improve algorithm performance in subregions of the space. An evaluation on six prediction tasks, ranging from detecting deception to differentiating impressionist artists, demonstrated that aggregating crowd features improves upon both asking the crowd for a direct prediction and off-the-shelf machine learning features by over 10%. Further, hybrid systems that use both crowd-nominated and machine-extracted features can outperform those that use either in isolation.

The web is a catalyst for drawing people together around shared goals, but many groups never reach critical mass. It can thus be risky to commit time or effort to a goal: participants show up only to discover that nobody else did, and organizers devote significant effort to causes that never get off the ground. Crowdfunding has lessened some of this risk by only calling in donations when an effort reaches a collective monetary goal. However, it leaves unsolved the harder problem of mobilizing effort, time and participation. We generalize the concept into activation thresholds, commitments that are conditioned on others' participation. With activation thresholds, supporters only need to show up for an event if enough other people commit as well. Catalyst is a platform that introduces activation thresholds for on-demand events. For more complex coordination needs, Catalyst also provides thresholds based on time or role (e.g., a bake sale requiring commitments for bakers, decorators, and sellers). In a multi-month field deployment, Catalyst helped users organize events including food bank volunteering, on-demand study groups, and mass participation events like a human chess game. Our results suggest that activation thresholds can indeed catalyze a large class of new collective efforts.

In story writing, the diverse perspectives of the crowd could support an author's search for the perfect character, setting, or plot. However, structuring crowd collaboration is challenging. Too little structure leads to unfocused, sprawling narratives, and too much structure stifles creativity. Motivated by the idea that individual creative leaders and the crowd have complementary creative strengths, we present an approach where a leader directs the high-level vision for a story and articulates creative constraints for the crowd. This approach is embodied in Ensemble, a novel collaborative story-writing platform. In a month-long short story competition, over one hundred volunteer users on the web started over fifty short stories using Ensemble. Leaders used the platform to direct collaborator work by establishing creative goals, and collaborators contributed meaningful, high-level ideas to stories through specific suggestions. This work suggests that asymmetric creative contributions may support a broad new class of creative collaborations.

On many social networking web sites such as Facebook and Twitter, resharing or reposting functionality allows users to share others' content with their own friends or followers. As content is reshared from user to user, large cascades of reshares can form. While a growing body of research has focused on analyzing and characterizing such cascades, a recent, parallel line of work has argued that the future trajectory of a cascade may be inherently unpredictable. In this work, we develop a framework for addressing cascade prediction problems. On a large sample of photo reshare cascades on Facebook, we find strong performance in predicting whether a cascade will continue to grow in the future. We find that the relative growth of a cascade becomes more predictable as we observe more of its reshares, that temporal and structural features are key predictors of cascade size, and that initially, breadth, rather than depth in a cascade is a better indicator of larger cascades. This prediction performance is robust in the sense that multiple distinct classes of features all achieve similar performance. We also discover that temporal features are predictive of a cascade's eventual shape. Observing independent cascades of the same content, we find that while these cascades differ greatly in size, we are still able to predict which ends up the largest.

Peer and self-assessment offer an opportunity to scale both assessment and learning to global classrooms. This article reports our experiences with two iterations of the first large online class to use peer and self-assessment. In this class, peer grades correlated highly with staff-assigned grades. The second iteration had 42.9% of students’ grades within 5% of the staff grade, and 65.5% within 10%. On average, students assessed their work 7% higher than staff did. Students also rated peers’ work from their own country 3.6% higher than those from elsewhere. We performed three experiments to improve grading accuracy. We found that giving students feedback about their grading bias increased subsequent accuracy. We introduce short, customizable feedback snippets that cover common issues with assignments, providing students more qualitative peer feedback. Finally, we introduce a data-driven approach that highlights high-variance items for improvement. We find that rubrics that use a parallel sentence structure, unambiguous wording, and well-specified dimensions have lower variance. After revising rubrics, median grading error decreased from 12.4% to 9.9%.

While there has been significant research around aspects of tagging systems such as the vocabulary people use and the reasons they tag, there has been little focus on the design of the tagging interface itself. This paper discusses how kultagg, a ludic interface that includes the ability to color tags and place them directly on images, affect people's behavior and attitudes toward tagging. We conducted interviews with 10 people, asking them to use and reflect on kultagg. Color plays a significant role in enhancing a user's interest and enjoyment in tagging and has uses from self-expression to organization. People appreciated on-image tagging for its personal nature, ease of use, and specificity, although these tags tended to be less abstract and holistic than tags created in a more typical interface. Participants' generally positive response to kultagg suggests that including ludic elements in task-oriented domains is useful in creating rich, expressive systems.

One of the major objectives of Advanced Traffic Management Systems (ATMS) is to reduce traffic congestion in urban environments by improving the efficiency of utilization of existing infrastructures. Many creative and efficient technologies have been developed over the years. Although, commuters especially drivers take a critical part in containing traffic congestion problems, they are playing a passive role in the traffic-management ecosystem. Considerably, this is due to the information asymmetry between ATMS decision makers and commuters; what is missing is a matching mechanism to create a bridge between information providers and information consumers in a mobility environment. We solve this dilemma through implementing visual pertinent information services for commuters. We use probe vehicles to estimate the real-time traffic flow and disseminate this information effectively to users' mobile devices. We propose a 2-level indexing scheme to effectively index the grid cells which contain the spatial information. Processed information is disseminated to users through wireless means and presented in a user friendly interface on users' mobile devices. We have implemented a location-aware mobile application and back-end services. Experimental results show that our system is effective and scalable.