When users post on social media, they protect their privacy by choosing an access control setting that is rarely revisited. Changes in users' lives and relationships, as well as social media platforms themselves, can cause mismatches between a post's active privacy setting and the desired setting. The importance of managing this setting combined with the high volume of potential friend-post pairs needing evaluation necessitate a semi-automated approach. We attack this problem through a combination of a user study and the development of automated inference of potentially mismatched privacy settings. A total of 78 Facebook users reevaluated the privacy settings for five of their Facebook posts, also indicating whether a selection of friends should be able to access each post. They also explained their decision. With this user data, we designed a classifier to identify posts with currently incorrect sharing settings. This classifier shows a 317% improvement over a baseline classifier based on friend interaction. We also find that many of the most useful features can be collected without user intervention, and we identify directions for improving the classifier's accuracy. CCS CONCEPTS • Security and privacy → Usability in security and privacy.

Background: The onset of the COVID-19 pandemic and the consequent “infodemic” increased concerns about Twitter’s role in advancing antivaccination messages, even before a vaccine became available to the public. New computational methods allow for analysis of cross-platform use by tracking links to websites shared over Twitter, which, in turn, can uncover some of the content and dynamics of information sources and agenda-setting processes. Such understanding can advance theory and efforts to reduce misinformation.Objective: Informed by agenda-setting theory, this study aimed to identify the content and temporal patterns of websites shared in vaccine-related tweets posted to COVID-19 conversations on Twitter between February and June 2020.Methods: We used triangulation of data analysis methods. Data mining consisted of the screening of around 5 million tweets posted to COVID-19 conversations to identify tweets that related to vaccination and including links to websites shared within these tweets. We further analyzed the content the 20 most-shared external websites using a mixed methods approach.Results: Of 841,896 vaccination-related tweets identified, 185,994 (22.1%) contained links to specific websites. A wide range of websites were shared, with the 20 most-tweeted websites constituting 14.5% (27,060/185,994) of the shared websites and typically being shared for only 2 to 3 days. Traditional media constituted the majority of these 20 websites, along with other social media and governmental sources. We identified markers of inauthentic propagation for some of these links.Conclusions: The topic of vaccination was prevalent in tweets about COVID-19 early in the pandemic. Sharing websites was a common communication strategy, and its “bursty” pattern and inauthentic propagation strategies pose challenges for health promotion efforts. Future studies should consider cross-platform use in dissemination of health information and in counteracting misinformation.

Ranking algorithms in online platforms serve not only users on the demand side, but also items on the supply side. While ranking has traditionally presented items in an order that maximizes their utility to users, the uneven interactions that different items receive as a result of such a ranking can pose item fairness concerns. Moreover, interaction is affected by various forms of bias, two of which have received considerable attention: position bias and selection bias. Position bias occurs due to lower likelihood of observation for items in lower ranked positions. Selection bias occurs because interaction is not possible with items below an arbitrary cutoff position chosen by the front-end application at deployment time (i.e., showing only the top- k items). A less studied, third form of bias, trust bias, is equally important, as it makes interaction dependent on rank even after observation, by influencing the item’s perceived relevance. To capture interaction disparity in the presence of all three biases, in this article, we introduce a flexible fairness metric. Using this metric, we develop a post-processing algorithm that optimizes fairness in ranking through greedy exploration and allows a tradeoff between fairness and utility. Our algorithm outperforms state-of-the-art fair ranking algorithms on several datasets.

While exposure to diverse viewpoints may reduce polarization, it can also have a backfire effect and exacerbate polarization when the discussion is adversarial. Here, we examine the question whether intergroup interactions around important events affect polarization between majority and minority groups in social networks. We compile data on the religious identity of nearly 700,000 Indian Twitter users engaging in COVID-19-related discourse during 2020. We introduce a new measure for an individual's group conformity based on contextualized embeddings of tweet text, which helps us assess polarization between religious groups. We then use a meta-learning framework to examine heterogeneous treatment effects of intergroup interactions on an individual's group conformity in the light of communal, political, and socio-economic events. We find that for political and social events, intergroup interactions reduce polarization. This decline is weaker for individuals at the extreme who already exhibit high conformity to their group. In contrast, during communal events, intergroup interactions can increase group conformity. Finally, we decompose the differential effects across religious groups in terms of emotions and topics of discussion. The results show that the dynamics of religious polarization are sensitive to the context and have important implications for understanding the role of intergroup interactions.

We present a visual computing framework for analysing moral rhetoric on social media around controversial topics. Using Moral Foundation Theory, we propose a methodology for deconstructing and visualizing the when, where and who behind each of these moral dimensions as expressed in microblog data. We characterize the design of this framework, developed in collaboration with experts from language processing, communications and causal inference. Our approach integrates microblog data with multiple sources of geospatial and temporal data, and leverages unsupervised machine learning (generalized additive models) to support collaborative hypothesis discovery and testing. We implement this approach in a system named MOTIV. We illustrate this approach on two problems, one related to Stay‐at‐home policies during the COVID‐19 pandemic, and the other related to the Black Lives Matter movement. Through detailed case studies and discussions with collaborators, we identify several insights discovered regarding the different drivers of moral sentiment in social media. Our results indicate that this visual approach supports rapid, collaborative hypothesis testing, and can help give insights into the underlying moral values behind controversial political issues.Supplemental Material: https://osf.io/ygkzn/?view_only=6310c0886938415391d977b8aae8b749