arXiv subjects

Kenneth Joseph

Publications and source records attributed to Kenneth Joseph.

33 records · Page 2Linked to original sources

arXiv2021

Local News Online and COVID in the U.S.: Relationships among Coverage, Cases, Deaths, and Audience

We present analyses from a real-time information monitoring system of online local news in the U.S. We study relationships among online local news coverage of COVID, cases and deaths in an area, and properties of local news outlets and their audiences. Our analysis relies on a unique dataset of the online content of over 300 local news outlets, encompassing over 750,000 articles over a period of 10 months spanning April 2020 to February 2021. We find that the rate of COVID coverage over time by local news outlets was primarily associated with death rates at the national level, but that this effect dissipated over the course of the pandemic as news about COVID was steadily displaced by sociopolitical events, like the 2020 U.S. elections. We also find that both the volume and content of COVID coverage differed depending on local politics, and outlet audience size, as well as evidence that more vulnerable populations received less pandemic-related news.

cs.SI↗

arXiv2021

Insidious Nonetheless: How Small Effects and Hierarchical Norms Create and Maintain Gender Disparities in Organizations

The term glass ceiling is applied to the well-established phenomenon in which women and people of color are consistently blocked from reaching the upper-most levels of the corporate hierarchy. Focusing on gender, we present an agent-based model that explores how empirically established mechanisms of interpersonal discrimination coevolve with social norms at both the organizational (meso) and societal (macro) levels to produce this glass ceiling effect for women. Our model extends our understanding of how the glass ceiling arises, and why it can be resistant to change. We do so by synthesizing existing psychological and structural theories of discrimination into a mathematical model that quantifies explicitly how complex organizational systems can produce and maintain inequality. We discuss implications of our findings for both intervention and future empirical analyses, and provide open-source code for those wishing to adapt or extend our work.

cs.SI↗

arXiv2021

Incentives in Two-sided Matching Markets with Prediction-enhanced Preference-formation

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. This economic model allows us to analyze adversarial interaction attacks. Finally, using school choice as an example, we build a simulation to show that, as the trust in and accuracy of predictions increases, schools gain progressively more by initiating an adversarial interaction attack. We also show that this attack increases inequality in the student population.

cs.LG↗

arXiv2021

(Mis)alignment Between Stance Expressed in Social Media Data and Public Opinion Surveys

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.

cs.SI↗

arXiv2021

A Method to Analyze Multiple Social Identities in Twitter Bios

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.

cs.SI↗

arXiv2021

Friend or Foe: A Review and Synthesis of Computational Models of the Identity Labeling Problem

We introduce the identity labeling problem - given an individual in a social situation, can we predict what identity(ies) they will be labeled with by someone else? This problem remains a theoretical gap and methodological challenge, evidenced by the fact that models of social-cognition often sidestep the issue by treating identities as already known. We build on insights from existing models to develop a new framework, entitled Latent Cognitive Social Spaces, that can incorporate multiple social cues including sentiment information, socio-demographic characteristics, and institutional associations to estimate the most culturally expected identity. We apply our model to data collected in two vignette experiments, finding that it predicts identity labeling choices of participants with a mean absolute error of 10.9%, a 100% improvement over previous models based on parallel constraint satisfaction and affect control theory.

cs.CY↗

arXiv2021

Who Gets What, According to Whom? An Analysis of Fairness Perceptions in Service Allocation

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.

cs.CY↗

arXiv2021

An Agent-based Model to Evaluate Interventions on Online Dating Platforms to Decrease Racial Homogamy

Perhaps the most controversial questions in the study of online platforms today surround the extent to which platforms can intervene to reduce the societal ills perpetrated on them. Up for debate is whether there exist any effective and lasting interventions a platform can adopt to address, e.g., online bullying, or if other, more far-reaching change is necessary to address such problems. Empirical work is critical to addressing such questions. But it is also challenging, because it is time-consuming, expensive, and sometimes limited to the questions companies are willing to ask. To help focus and inform this empirical work, we here propose an agent-based modeling (ABM) approach. As an application, we analyze the impact of a set of interventions on a simulated online dating platform on the lack of long-term interracial relationships in an artificial society. In the real world, a lack of interracial relationships are a critical vehicle through which inequality is maintained. Our work shows that many previously hypothesized interventions online dating platforms could take to increase the number of interracial relationships from their website have limited effects, and that the effectiveness of any intervention is subject to assumptions about sociocultural structure. Further, interventions that are effective in increasing diversity in long-term relationships are at odds with platforms' profit-oriented goals. At a general level, the present work shows the value of using an ABM approach to help understand the potential effects and side effects of different interventions that a platform could take.

cs.CY↗

arXiv2020

An analysis of replies to Trump's tweets

Donald Trump has tweeted thousands of times during his presidency. These public statements are an increasingly important way through which Trump communicates his political and personal views. A better understanding of the way the American public consumes and responds to these tweets is therefore critical. In the present work, we address both consumption of and response to Trump's tweets by studying replies to them on Twitter. With respect to response, we find that a small number of older, white, left-leaning, and female Americans are responsible for the vast majority of replies to Trump's tweets. These individuals also attend to a broader range of Trump's tweets than the rest of the individuals we study. With respect to consumption, we note that Trump's tweets are often viewed not in isolation, but rather in the context of a set of algorithmically-curated replies. These replies may therefore color the way Americans consume Trump's tweets. To this end, we find some evidence that Twitter accounts see replies in line with their political leanings. However, we show that this can be largely, although not entirely, attributed to the fact that Twitter is more likely to show replies by accounts a user follows. As a basis for comparison, all results for Trump are compared and contrasted with replies to Joe Biden's tweets.

cs.CY↗

arXiv2020

Explaining Gender Differences in Academics' Career Trajectories

Academic fields exhibit substantial levels of gender segregation. To date, most attempts to explain this persistent global phenomenon have relied on limited cross-sections of data from specific countries, fields, or career stages. Here we used a global longitudinal dataset assembled from profiles on ORCID.org to investigate which characteristics of a field predict gender differences among the academics who leave and join that field. Only two field characteristics consistently predicted such differences: (1) the extent to which a field values raw intellectual talent ("brilliance") and (2) whether a field is in Science, Technology, Engineering, and Mathematics (STEM). Women more than men moved away from brilliance-oriented and STEM fields, and men more than women moved toward these fields. Our findings suggest that stereotypes associating brilliance and other STEM-relevant traits with men more than women play a key role in maintaining gender segregation across academia.

cs.SI↗

arXiv2020

MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline

Existing methods for debiasing word embeddings often do so only superficially, in that words that are stereotypically associated with, e.g., a particular gender in the original embedding space can still be clustered together in the debiased space. However, there has yet to be a study that explores why this residual clustering exists, and how it might be addressed. The present work fills this gap. We identify two potential reasons for which residual bias exists and develop a new pipeline, MDR Cluster-Debias, to mitigate this bias. We explore the strengths and weaknesses of our method, finding that it significantly outperforms other existing debiasing approaches on a variety of upstream bias tests but achieves limited improvement on decreasing gender bias in a downstream task. This indicates that word embeddings encode gender bias in still other ways, not necessarily captured by upstream tests.

cs.CL↗

arXiv2020

When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People?

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.

cs.CL↗

arXiv2020

Theory In, Theory Out: The uses of social theory in machine learning for social science

Research at the intersection of machine learning and the social sciences has provided critical new insights into social behavior. At the same time, a variety of critiques have been raised ranging from technical issues with the data used and features constructed, problematic assumptions built into models, their limited interpretability, and their contribution to bias and inequality. We argue such issues arise primarily because of the lack of social theory at various stages of the model building and analysis. In the first half of this paper, we walk through how social theory can be used to answer the basic methodological and interpretive questions that arise at each stage of the machine learning pipeline. In the second half, we show how theory can be used to assess and compare the quality of different social learning models, including interpreting, generalizing, and assessing the fairness of models. We believe this paper can act as a guide for computer and social scientists alike to navigate the substantive questions involved in applying the tools of machine learning to social data.

cs.CY↗

arXiv2017

Exploring the Ideological Nature of Journalists' Social Networks on Twitter and Associations with News Story Content

The present work proposes the use of social media as a tool for better understanding the relationship between a journalists' social network and the content they produce. Specifically, we ask: what is the relationship between the ideological leaning of a journalist's social network on Twitter and the news content he or she produces? Using a novel dataset linking over 500,000 news articles produced by 1,000 journalists at 25 different news outlets, we show a modest correlation between the ideologies of who a journalist follows on Twitter and the content he or she produces. This research can provide the basis for greater self-reflection among media members about how they source their stories and how their own practice may be colored by their online networks. For researchers, the findings furnish a novel and important step in better understanding the construction of media stories and the mechanics of how ideology can play a role in shaping public information.

cs.SI↗

arXiv2017

ConStance: Modeling Annotation Contexts to Improve Stance Classification

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.

cs.SI↗