Social media platforms provide users with a profile description field, commonly known as a "bio," where they can present themselves to the world. A growing literature shows that text in these bios can improve our understanding of online self-presentation and behavior, but existing work relies exclusively on keyword-based approaches to do so. We here propose and evaluate a suite of simple, effective, and theoretically motivated approaches to embed bios in spaces that capture salient dimensions of social meaning, such as age and partisanship. We evaluate our methods on four tasks, showing that the strongest one out-performs several practical baselines. We then show the utility of our method in helping understand associations between self-presentation and the sharing of URLs from low-quality news sites on Twitter, with a particular focus on explore the interactions between age and partisanship, and exploring the effects of self-presentations of religiosity. Our work provides new tools to help computational social scientists make use of information in bios, and provides new insights into how misinformation sharing may be perceived on Twitter.

During a natural disaster, people post text messages on various platforms, such as social media and short message service (SMS) platforms, to share urgent information and seek help. Many text messages contain location descriptions about victims and accidents. Accurately extracting these location descriptions can help disaster responders reach victims more quickly and even save lives. These location descriptions, however, are often more complex than simple place names (e.g. city names), and cannot be extracted using typical named entity recognition approaches. While new machine learning models could be trained, they require labeled training data that are time-consuming to create without an effective data annotation tool. To fill this gap, we develop GALLOC, a GeoAnnotator for Labeling LOCation descriptions from disaster-related text messages. GALLOC is an open-source and Web-based tool that provides a variety of functions for supporting location description annotation, such as artificial intelligence powered pre-annotation and automatic spatial footprint identification. It also supports multilingual data annotation, and can be used by a group of users to collaboratively create a dataset. We present the design considerations and functions of GALLOC and evaluate it via a comparison with previous tools and an experiment to annotate a small set of disaster-related messages.

Social media has been at the center of discussions about political polarization in the United States. However, scholars are actively debating both the scale of political polarization online, and how important online polarization is to the offline world. One question at the center of this debate is what interactions across parties look like online, and in particular 1) whether increasing the number of such interactions is likely to increase or reduce polarization, and 2) what technological affordances may make it more likely that these cross-party interactions benefit, rather than detract from, existing political challenges. The present work aims to provide insights into the latter; that is, we focus on providing a better understanding of how a set of 400,000 partisan users on a particular social media platform, Twitter, used the platform's affordances to interact within and across parties in a large dataset of tweets about COVID in 2021. Our findings suggest that Republican use of cross-party interaction were both more potent and potentially more strategic during COVID, that cross-party interaction was driven heavily by a small set of users and conversations, and that there exist non-obvious indirect pathways to cross-party exposure when different modes of interaction are chained together (especially retweets of quotes). These findings have implications beyond Twitter, we believe, in understanding how affordances of platforms can help to shape partisan exposure and interaction.

At the end of October 2022, Elon Musk concluded his acquisition of Twitter. In the weeks and months before that, several questions were publicly discussed that were not only of interest to the platform's future buyers, but also of high relevance to the Computational Social Science research community. For example, how many active users does the platform have? What percentage of accounts on the site are bots? And, what are the dominating topics and sub-topical spheres on the platform? In a globally coordinated effort of 80 scholars to shed light on these questions, and to offer a dataset that will equip other researchers to do the same, we have collected all 375 million tweets published within a 24-hour time period starting on September 21, 2022. To the best of our knowledge, this is the first complete 24-hour Twitter dataset that is available for the research community. With it, the present work aims to accomplish two goals. First, we seek to answer the aforementioned questions and provide descriptive metrics about Twitter that can serve as references for other researchers. Second, we create a baseline dataset for future research that can be used to study the potential impact of the platform's ownership change.

Two-sided matching markets have long existed to pair agents in the absence of regulated exchanges. A common example is school choice, where a matching mechanism uses student and school preferences to assign students to schools. In such settings, forming preferences is both difficult and critical. Prior work has suggested various prediction mechanisms that help agents make decisions about their preferences. Although often deployed together, these matching and prediction mechanisms are almost always analyzed separately. The present work shows that at the intersection of the two lies a previously unexplored type of strategic behavior: agents returning to the market (e.g., schools) can attack future predictions by interacting short-term non-optimally with their matches. Here, we first introduce this type of strategic behavior, which we call an adversarial interaction attack. Next, we construct a formal economic model that captures the feedback loop between prediction mechanisms designed to assist agents and the matching mechanism used to pair them. Finally, in a simplified setting, we prove that returning agents can benefit from using adversarial interaction attacks and gain progressively more as the trust in and accuracy of predictions increases. We also show that this attack increases inequality in the student population.

Social media messages posted by people during natural disasters often contain important location descriptions, such as the locations of victims. Recent research has shown that many of these location descriptions go beyond simple place names, such as city names and street names, and are difficult to extract using typical named entity recognition (NER) tools. While advanced machine learning models could be trained, they require large labeled training datasets that can be time-consuming and labor-intensive to create. In this work, we propose a method that fuses geo-knowledge of location descriptions and a Generative Pre-trained Transformer (GPT) model, such as ChatGPT and GPT-4. The result is a geo-knowledge-guided GPT model that can accurately extract location descriptions from disaster-related social media messages. Also, only 22 training examples encoding geo-knowledge are used in our method. We conduct experiments to compare this method with nine alternative approaches on a dataset of tweets from Hurricane Harvey. Our method demonstrates an over 40% improvement over typically used NER approaches. The experiment results also show that geo-knowledge is indispensable for guiding the behavior of GPT models. The extracted location descriptions can help disaster responders reach victims more quickly and may even save lives.

Algorithmic fairness research has traditionally been linked to the disciplines of philosophy, ethics, and economics, where notions of fairness are prescriptive and seek objectivity. Increasingly, however, scholars are turning to the study of what different people perceive to be fair, and how these perceptions can or should help to shape the design of machine learning, particularly in the policy realm. The present work experimentally explores five novel research questions at the intersection of the "Who," "What," and "How" of fairness perceptions. Specifically, we present the results of a multi-factor conjoint analysis study that quantifies the effects of the specific context in which a question is asked, the framing of the given question, and who is answering it. Our results broadly suggest that the "Who" and "What," at least, matter in ways that are 1) not easily explained by any one theoretical perspective, 2) have critical implications for how perceptions of fairness should be measured and/or integrated into algorithmic decision-making systems.

Stance detection, which aims to determine whether an individual is for or against a target concept, promises to uncover public opinion from large streams of social media data.Yet even human annotation of social media content does not always capture "stance" as measured by public opinion polls.We demonstrate this by directly comparing an individual's self-reported stance to the stance inferred from their social media data.Leveraging a longitudinal public opinion survey with respondent Twitter handles, we conducted this comparison for 1,129 individuals across four salient targets.We find that recall is high for both "Pro" and "Anti" stance classifications but precision is variable in a number of cases.We identify three factors leading to the disconnect between text and author stance: temporal inconsistencies, differences in constructs, and measurement errors from both survey respondents and annotators.By presenting a framework for assessing the limitations of stance detection models, this work provides important insight into what stance detection truly measures.

Twitter users signal social identity in their profile descriptions, or bios, in a number of important but complex ways that are not well-captured by existing characterizations of how identity is expressed in language. Better ways of defining and measuring these expressions may therefore be useful both in understanding how social identity is expressed in text, and how the self is presented on Twitter. To this end, the present work makes three contributions. First, using qualitative methods, we identify and define the concept of a personal identifier, which is more representative of the ways in which identity is signaled in Twitter bios. Second, we propose a method to extract all personal identifiers expressed in a given bio. Finally, we present a series of validation analyses that explore the strengths and limitations of our proposed method. Our work opens up exciting new opportunities at the intersection between the social psychological study of social identity and the study of how we compose the self through markers of identity on Twitter and in social media more generally.

Social biases are encoded in word embeddings.This presents a unique opportunity to study society historically and at scale, and a unique danger when embeddings are used in downstream applications.Here, we investigate the extent to which publicly-available word embeddings accurately reflect beliefs about certain kinds of people as measured via traditional survey methods.We find that biases found in word embeddings do, on average, closely mirror survey data across seventeen dimensions of social meaning.However, we also find that biases in embeddings are much more reflective of survey data for some dimensions of meaning (e.g.gender) than others (e.g.race), and that we can be highly confident that embedding-based measures reflect survey data only for the most salient biases.

There is a growing consensus that online platforms have a systematic influence on the democratic process. However, research beyond social media is limited. In this paper, we report the results of a mixed-methods algorithm audit of partisan audience bias and personalization within Google Search. Following Donald Trump's inauguration, we recruited 187 participants to complete a survey and install a browser extension that enabled us to collect Search Engine Results Pages (SERPs) from their computers. To quantify partisan audience bias, we developed a domain-level score by leveraging the sharing propensities of registered voters on a large Twitter panel. We found little evidence for the "filter bubble'' hypothesis. Instead, we found that results positioned toward the bottom of Google SERPs were more left-leaning than results positioned toward the top, and that the direction and magnitude of overall lean varied by search query, component type (e.g. "answer boxes"), and other factors. Utilizing rank-weighted metrics that we adapted from prior work, we also found that Google's rankings shifted the average lean of SERPs to the right of their unweighted average.

Social identities carry widely agreed upon meanings, called stereotypes, that have important effects on social processes. In the present work, we develop a method to extract the stereotypes of Twitter users. Our method is grounded in two distinct strands of theory, one that represents stereotypes as identities' affective meanings and the other that represents stereotypes as semantic relationships between identities. After validating our approach via a prediction task, we apply the model to a dataset of 45 thousand Twitter users who actively tweeted about the Michael Brown and Eric Garner tragedies. Our work provides unique insights into the stereotypes of these users, as well as providing a way of quantifying stereotypes that blends existing sociological and psychological theory in a novel, parsimonious way.

Manual annotations are a prerequisite for many applications of machine learning.However, weaknesses in the annotation process itself are easy to overlook.In particular, scholars often choose what information to give to annotators without examining these decisions empirically.For subjective tasks such as sentiment analysis, sarcasm, and stance detection, such choices can impact results.Here, for the task of political stance detection on Twitter, we show that providing too little context can result in noisy and uncertain annotations, whereas providing too strong a context may cause it to outweigh other signals.To characterize and reduce these biases, we develop ConStance, a general model for reasoning about annotations across information conditions.Given conflicting labels produced by multiple annotators seeing the same instances with different contexts, ConStance simultaneously estimates gold standard labels and also learns a classifier for new instances.We show that the classifier learned by ConStance outperforms a variety of baselines at predicting political stance, while the model's interpretable parameters shed light on the effects of each context.

Adverse events between police and the public, such as deadly shootings or instances of racial profiling, can cause serious or deadly harm, damage police legitimacy, and result in costly litigation. Evidence suggests these events can be prevented by targeting interventions based on an Early Intervention System (EIS) that flags police officers who are at a high risk for involvement in such adverse events. Today's EIS are not data-driven and typically rely on simple thresholds based entirely on expert intuition. In this paper, we describe our work with the Charlotte-Mecklenburg Police Department (CMPD) to develop a machine learning model to predict which officers are at risk for an adverse event. Our approach significantly outperforms CMPD's existing EIS, increasing true positives by ~12% and decreasing false positives by ~32%. Our work also sheds light on features related to officer characteristics, situational factors, and neighborhood factors that are predictive of adverse events. This work provides a starting point for police departments to take a comprehensive, data-driven approach to improve policing and reduce harm to both officers and members of the public.

Sociologists have long been interested in the ways that identities, or labels for people, are created, used and applied across various social contexts. The present work makes two contributions to the study of identity, in particular the study of identity in text. We first consider the following novel NLP task: given a set of text data (here, from Twitter), label each word in the text as being representative of a (possibly multi-word) identity. To address this task, we develop a comprehensive feature set that leverages several avenues of recent NLP work on Twitter and use these features to train a supervised classifier. Our model outperforms a surprisingly strong rule-based baseline by 33%. We then use our model for a case study, applying it to a large corpora of Twitter data from users who actively discussed the Eric Garner and Michael Brown cases. Among other findings, we observe that the identities used by individuals differ in interesting ways based on social context measures derived from census data.

Social media is rapidly becoming one of the mediums of choice for understanding the cultural pulse of a region; e.g., for identifying what the population is concerned with and what kind of help is needed in a crisis. To assess this cultural pulse it is critical to have an accurate assessment of who is saying what in social media. However, social media is also the home of malicious users engaged in disruptive, disingenuous, and potentially illegal activity. A range of users, both human and non-human, carry out such social cyber-attacks. We ask, to what extent does the presence or absence of such users influence our ability to assess the cultural pulse of a region? We conduct a series of experiments to analyze the fragility of social network assessments based on Twitter data by comparing changes in both the structural and content results when suspended users are left in and taken out. Because a Twitter account can be suspended for various reasons including spamming or spreading ideas that can lead to extremism or terrorism, we separately assess the impacts of removing apparent spam bots and apparent extremists. Experimental results demonstrate that Twitter-based network structures and content are unstable, and can be highly impacted by the removal of suspended users. Further, the results exhibit regional and temporal variation that may be related to the political situation or civil unrest. We also provides guidance on the differential impact of different types of potentially suspendable users.

Peter Blau was one of the first to define a latent social space and utilize it to provide concrete hypotheses. Blau defines social structure via social “parameters” (constraints). Actors that are closer together (more homogenous) in this social parameter space are more likely to interact. One of Blau’s most important hypotheses resulting from this work was that the consolidation of parameters could lead to isolated social groups. For example, the consolidation of race and income might lead to segregation. In the present work, we use Foursquare data from New York City to explore evidence of homogeneity along certain social parameters and consolidation that breeds social isolation in communities of locations checked in to by similar users. More specifically, we first test the extent to which communities detected via Latent Dirichlet Allocation are homogenous across a set of four social constraints—racial homophily, income homophily, personal interest homophily and physical space. Using a bootstrapping approach, we find that 14 (of 20) communities are statistically, and all but one qualitatively, homogenous along one of these social constraints, showing the relevance of Blau’s latent space model in venue communities determined via user check-in behavior. We then consider the extent to which communities with consolidated parameters, those homogenous on more than one parameter, represent socially isolated populations. We find communities homogenous on multiple parameters, including a homosexual community and a “hipster” community, that show support for Blau’s hypothesis that consolidation breeds social isolation. We consider these results in the context of mediated communication, in particular in the context of self-representation on social media.

We propose a system which allows users to select how and with whom they are available for contact by managing a set of personal "identities" and budding relationships. The most important of these media are public displays, which allow a low-cost barrier for finding potential friends through interaction via the display and through the attendance of displayed social events. In helping two people to both become aware of each other's existence and to pick media which suit their preferences, we believe such a system can increase the odds of two strangers forming a strong social bond.

In this work, we use foursquare check-ins to cluster users via topic modeling, a technique commonly used to classify text documents according to latent "themes". Here, however, the latent variables which group users can be thought of not as themes but rather as factors which drive check in behaviors, allowing for a qualitative understanding of influences on user check ins. Our model is agnostic of geo-spatial location, time, users' friends on social networking sites and the venue categories-we treat the existence of and intricate interactions between these factors as being latent, allowing them to emerge entirely from the data. We instantiate our model on data from New York and the San Francisco Bay Area and find evidence that the model is able to identify groups of people which are of different types (e.g. tourists), communities (e.g. users tightly clustered in space) and interests (e.g. people who enjoy athletics).