arXiv subjects

Kristina Lerman

Publications and source records attributed to Kristina Lerman.

At least 109 records · Page 6Linked to original sources

arXiv2021

Speaker Turn Modeling for Dialogue Act Classification

Dialogue Act (DA) classification is the task of classifying utterances with respect to the function they serve in a dialogue. Existing approaches to DA classification model utterances without incorporating the turn changes among speakers throughout the dialogue, therefore treating it no different than non-interactive written text. In this paper, we propose to integrate the turn changes in conversations among speakers when modeling DAs. Specifically, we learn conversation-invariant speaker turn embeddings to represent the speaker turns in a conversation; the learned speaker turn embeddings are then merged with the utterance embeddings for the downstream task of DA classification. With this simple yet effective mechanism, our model is able to capture the semantics from the dialogue content while accounting for different speaker turns in a conversation. Validation on three benchmark public datasets demonstrates superior performance of our model.

cs.CL↗

arXiv2021

DoGR: Disaggregated Gaussian Regression for Reproducible Analysis of Heterogeneous Data

Quantitative analysis of large-scale data is often complicated by the presence of diverse subgroups, which reduce the accuracy of inferences they make on held-out data. To address the challenge of heterogeneous data analysis, we introduce DoGR, a method that discovers latent confounders by simultaneously partitioning the data into overlapping clusters (disaggregation) and modeling the behavior within them (regression). When applied to real-world data, our method discovers meaningful clusters and their characteristic behaviors, thus giving insight into group differences and their impact on the outcome of interest. By accounting for latent confounders, our framework facilitates exploratory analysis of noisy, heterogeneous data and can be used to learn predictive models that better generalize to new data. We provide the code to enable others to use DoGR within their data analytic workflows.

cs.LG↗

arXiv2021

Mapping Moral Valence of Tweets Following the Killing of George Floyd

The viral video documenting the killing of George Floyd by Minneapolis police officer Derek Chauvin inspired nation-wide protests that brought national attention to widespread racial injustice and biased policing practices towards black communities in the United States. The use of social media by the Black Lives Matter movement was a primary route for activists to promote the cause and organize over 1,400 protests across the country. Recent research argues that moral discussions on social media are a catalyst for social change. This study sought to shed light on the moral dynamics shaping Black Lives Matter Twitter discussions by analyzing over 40,000 Tweets geo-located to Los Angeles. The goal of this study is to (1) develop computational techniques for mapping the structure of moral discourse on Twitter and (2) understand the connections between social media activism and protest.

cs.SI↗

arXiv2021

Pattern Discovery in Time Series with Byte Pair Encoding

The growing popularity of wearable sensors has generated large quantities of temporal physiological and activity data. Ability to analyze this data offers new opportunities for real-time health monitoring and forecasting. However, temporal physiological data presents many analytic challenges: the data is noisy, contains many missing values, and each series has a different length. Most methods proposed for time series analysis and classification do not handle datasets with these characteristics nor do they offer interpretability and explainability, a critical requirement in the health domain. We propose an unsupervised method for learning representations of time series based on common patterns identified within them. The patterns are, interpretable, variable in length, and extracted using Byte Pair Encoding compression technique. In this way the method can capture both long-term and short-term dependencies present in the data. We show that this method applies to both univariate and multivariate time series and beats state-of-the-art approaches on a real world dataset collected from wearable sensors.

eess.SP↗

arXiv2021

Emergence of Structural Inequalities in Scientific Citation Networks

Structural inequalities persist in society, conferring systematic advantages to some people at the expense of others, for example, by giving them substantially more influence and opportunities. Using bibliometric data about authors of scientific publications, we identify two types of structural inequalities in scientific citations. First, female authors, who represent a minority of researchers, receive less recognition for their work (through citations) relative to male authors; second, authors affiliated with top-ranked institutions, who are also a minority, receive substantially more recognition compared to other authors. We present a model for the growth of directed citation networks and show that citations disparities arise from individual preferences to cite authors from the same group (homophily), highly cited or active authors (preferential attachment), as well as the size of the group and how frequently new authors join. We analyze the model and show that its predictions align well with real-world observations. Our theoretical and empirical analysis also suggests potential strategies to mitigate structural inequalities in science. In particular, we find that merely increasing the minority group size does little to narrow the disparities. Instead, reducing the homophily of each group, frequently adding new authors to a research field while providing them an accessible platform among existing, established authors, together with balanced group sizes can have the largest impact on reducing inequality. Our work highlights additional complexities of mitigating structural disparities stemming from asymmetric relations (e.g., directed citations) compared to symmetric relations (e.g., collaborations).

physics.soc-ph↗

arXiv2021

Limiting Tags Fosters Efficiency

Tagging facilitates information retrieval in social media and other online communities by allowing users to organize and describe online content. Researchers found that the efficiency of tagging systems steadily decreases over time, because tags become less precise in identifying specific documents, i.e., they lose their descriptiveness. However, previous works did not answer how or even whether community managers can improve the efficiency of tags. In this work, we use information-theoretic measures to track the descriptive and retrieval efficiency of tags on Stack Overflow, a question-answering system that strictly limits the number of tags users can specify per question. We observe that tagging efficiency stabilizes over time, while tag content and descriptiveness both increase. To explain this observation, we hypothesize that limiting the number of tags fosters novelty and diversity in tag usage, two properties which are both beneficial for tagging efficiency. To provide qualitative evidence supporting our hypothesis, we present a statistical model of tagging that demonstrates how novelty and diversity lead to greater tag efficiency in the long run. Our work offers insights into policies to improve information organization and retrieval in online communities.

cs.CY↗

arXiv2021

Gender disparity in the authorship of biomedical research publications during the COVID-19 pandemic

Preliminary evidence suggests that women, including female researchers, are disproportionately affected by the COVID-19 pandemic in terms of unequal distribution of childcare, elderly care and other kinds of domestic and emotional labor. Sudden lockdowns and abrupt shifts in daily routines have disproportionate consequences on their productivity, which is reflected by a sudden drop in research output in biomedical research, consequently affecting the number of female authors of scientific publications. We investigate the proportion of male and female researchers who published scientific papers during the COVID-19 pandemic, using bibliometric data from biomedical preprint servers and selected Springer-Nature journals. Our findings document a decrease in the number of publications by female authors in biomedical field during the global pandemic. This effect is particularly pronounced for papers related to COVID-19, indicating that women are producing fewer publications related to COVID-19 research. This sudden increase in the gender gap is persistent across the ten countries with the highest number of researchers. These results should be used to inform the scientific community of the worrying trend in COVID-19 research and the disproportionate effect that the pandemic has on female academics.

cs.DL↗

arXiv2021

A Directed, Bi-Populated Preferential Attachment Model with Applications to Analyzing the Glass Ceiling Effect

Preferential attachment, homophily and, their consequences such as the glass ceiling effect have been well-studied in the context of undirected networks. However, the lack of an intuitive, theoretically tractable model of a directed, bi-populated~(i.e.,~containing two groups) network with variable levels of preferential attachment, homophily and growth dynamics~(e.g.,~the rate at which new nodes join, whether the new nodes mostly follow existing nodes or the existing nodes follow them, etc.) has largely prevented such consequences from being explored in the context of directed networks, where they more naturally occur due to the asymmetry of links. To this end, we present a rigorous theoretical analysis of the \emph{Directed Mixed Preferential Attachment} model and, use it to analyze the glass ceiling effect in directed networks. More specifically, we derive the closed-form expressions for the power-law exponents of the in- and out- degree distributions of each group~(minority and majority) and, compare them with each other to obtain insights. In particular, our results yield answers to questions such as: \emph{when does the minority group have a heavier out-degree (or in-degree) distribution compared to the majority group? what effect does frequent addition of edges between existing nodes have on the in- and out- degree distributions of the majority and minority groups?}. Such insights shed light on the interplay between the structure~(i.e., the in- and out- degree distributions of the two groups) and dynamics~(characterized collectively by the homophily, preferential attachment, group sizes and growth dynamics) of various real-world networks. Finally, we utilize the obtained analytical results to characterize the conditions under which the glass ceiling effect emerge in a directed network. Our analytical results are supported by detailed numerical results.

cs.SI↗

arXiv2021

Individualized Context-Aware Tensor Factorization for Online Games Predictions

Individual behavior and decisions are substantially influenced by their contexts, such as location, environment, and time. Changes along these dimensions can be readily observed in Multiplayer Online Battle Arena games (MOBA), where players face different in-game settings for each match and are subject to frequent game patches. Existing methods utilizing contextual information generalize the effect of a context over the entire population, but contextual information tailored to each individual can be more effective. To achieve this, we present the Neural Individualized Context-aware Embeddings (NICE) model for predicting user performance and game outcomes. Our proposed method identifies individual behavioral differences in different contexts by learning latent representations of users and contexts through non-negative tensor factorization. Using a dataset from the MOBA game League of Legends, we demonstrate that our model substantially improves the prediction of winning outcome, individual user performance, and user engagement.

cs.AI↗

arXiv2021

The Emergence of Heterogeneous Scaling in Research Institutions

Research institutions provide the infrastructure for scientific discovery, yet their role in the production of knowledge is not well characterized. To address this gap, we analyze interactions of researchers within and between institutions from millions of scientific papers. Our analysis reveals that the number of collaborations scales superlinearly with institution size, though at different rates (heterogeneous densification). We also find that the number of institutions scales with the number of researchers as a power law (Heaps' law) and institution sizes approximate Zipf's law. These patterns can be reproduced by a simple model with three mechanisms: (i) researchers collaborate with friends-of-friends, (ii) new institutions trigger more potential institutions, and (iii) researchers are preferentially hired by large institutions. This model reveals an economy of scale in research: larger institutions grow faster and amplify collaborations. Our work provides a new understanding of emergent behavior in research institutions and how they facilitate innovation.

physics.soc-ph↗

arXiv2021

A Model of Densifying Collaboration Networks

Research collaborations provide the foundation for scientific advances, but we have only recently begun to understand how they form and grow on a global scale. Here we analyze a model of the growth of research collaboration networks to explain the empirical observations that the number of collaborations scales superlinearly with institution size, though at different rates (heterogeneous densification), the number of institutions grows as a power of the number of researchers (Heaps' law) and institution sizes approximate Zipf's law. This model has three mechanisms: (i) researchers are preferentially hired by large institutions, (ii) new institutions trigger more potential institutions, and (iii) researchers collaborate with friends-of-friends. We show agreement between these assumptions and empirical data, through analysis of co-authorship networks spanning two centuries. We then develop a theoretical understanding of this model, which reveals emergent heterogeneous scaling such that the number of collaborations between institutions scale with an institution's size.

physics.soc-ph↗

arXiv2020

TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers

We present a novel longitudinal multimodal corpus of physiological and behavioral data collected from direct clinical providers in a hospital workplace. We designed the study to investigate the use of off-the-shelf wearable and environmental sensors to understand individual-specific constructs such as job performance, interpersonal interaction, and well-being of hospital workers over time in their natural day-to-day job settings. We collected behavioral and physiological data from $n = 212$ participants through Internet-of-Things Bluetooth data hubs, wearable sensors (including a wristband, a biometrics-tracking garment, a smartphone, and an audio-feature recorder), together with a battery of surveys to assess personality traits, behavioral states, job performance, and well-being over time. Besides the default use of the data set, we envision several novel research opportunities and potential applications, including multi-modal and multi-task behavioral modeling, authentication through biometrics, and privacy-aware and privacy-preserving machine learning.

eess.SP↗

arXiv2020

Political Partisanship and Anti-Science Attitudes in Online Discussions about Covid-19

The novel coronavirus pandemic continues to ravage communities across the US. Opinion surveys identified importance of political ideology in shaping perceptions of the pandemic and compliance with preventive measures. Here, we use social media data to study complexity of polarization. We analyze a large dataset of tweets related to the pandemic collected between January and May of 2020, and develop methods to classify the ideological alignment of users along the moderacy (hardline vs moderate), political (liberal vs conservative) and science (anti-science vs pro-science) dimensions. While polarization along the science and political dimensions are correlated, politically moderate users are more likely to be aligned with the pro-science views, and politically hardline users with anti-science views. Contrary to expectations, we do not find that polarization grows over time; instead, we see increasing activity by moderate pro-science users. We also show that anti-science conservatives tend to tweet from the Southern US, while anti-science moderates from the Western states. Our findings shed light on the multi-dimensional nature of polarization, and the feasibility of tracking polarized opinions about the pandemic across time and space through social media data.

cs.SI↗

arXiv2020

Inherent Trade-offs in the Fair Allocation of Treatments

Explicit and implicit bias clouds human judgement, leading to discriminatory treatment of minority groups. A fundamental goal of algorithmic fairness is to avoid the pitfalls in human judgement by learning policies that improve the overall outcomes while providing fair treatment to protected classes. In this paper, we propose a causal framework that learns optimal intervention policies from data subject to fairness constraints. We define two measures of treatment bias and infer best treatment assignment that minimizes the bias while optimizing overall outcome. We demonstrate that there is a dilemma of balancing fairness and overall benefit; however, allowing preferential treatment to protected classes in certain circumstances (affirmative action) can dramatically improve the overall benefit while also preserving fairness. We apply our framework to data containing student outcomes on standardized tests and show how it can be used to design real-world policies that fairly improve student test scores. Our framework provides a principled way to learn fair treatment policies in real-world settings.

cs.LG↗

arXiv2020

Origins of Algorithmic Instabilities in Crowdsourced Ranking

Crowdsourcing systems aggregate decisions of many people to help users quickly identify high-quality options, such as the best answers to questions or interesting news stories. A long-standing issue in crowdsourcing is how option quality and human judgement heuristics interact to affect collective outcomes, such as the perceived popularity of options. We address this limitation by conducting a controlled experiment where subjects choose between two ranked options whose quality can be independently varied. We use this data to construct a model that quantifies how judgement heuristics and option quality combine when deciding between two options. The model reveals popularity-ranking can be unstable: unless the quality difference between the two options is sufficiently high, the higher quality option is not guaranteed to be eventually ranked on top. To rectify this instability, we create an algorithm that accounts for judgement heuristics to infer the best option and rank it first. This algorithm is guaranteed to be optimal if data matches the model. When the data does not match the model, however, simulations show that in practice this algorithm performs better or at least as well as popularity-based and recency-based ranking for any two-choice question. Our work suggests that algorithms relying on inference of mathematical models of user behavior can substantially improve outcomes in crowdsourcing systems.

cs.SI↗

arXiv2020

The Leaky Pipeline in Physics Publishing

Women make up a shrinking portion of physics faculty in senior positions, a phenomenon known as a "leaky pipeline." While fixing this problem has been a priority in academic institutions, efforts have been stymied by the diverse sources of leaks. In this paper we identify a bias potentially contributing to the leaky pipeline. We analyze bibliographic data provided by the American Physical Society (APS), a leading publisher of physics research. By inferring the gender of authors from names, we are able to measure the fraction of women authors over past decades. We show that the more selective, higher impact APS journals have lower fractions of women authors compared to other APS journals. Correcting this bias may help more women publish in prestigious APS journals, and in turn help improve their academic promotion cases.

physics.soc-ph↗

arXiv2020

Follow the Leader: Documents on the Leading Edge of Semantic Change Get More Citations

Diachronic word embeddings -- vector representations of words over time -- offer remarkable insights into the evolution of language and provide a tool for quantifying sociocultural change from text documents. Prior work has used such embeddings to identify shifts in the meaning of individual words. However, simply knowing that a word has changed in meaning is insufficient to identify the instances of word usage that convey the historical or the newer meaning. In this paper, we link diachronic word embeddings to documents, by situating those documents as leaders or laggards with respect to ongoing semantic changes. Specifically, we propose a novel method to quantify the degree of semantic progressiveness in each word usage, and then show how these usages can be aggregated to obtain scores for each document. We analyze two large collections of documents, representing legal opinions and scientific articles. Documents that are scored as semantically progressive receive a larger number of citations, indicating that they are especially influential. Our work thus provides a new technique for identifying lexical semantic leaders and demonstrates a new link between progressive use of language and influence in a citation network.

cs.CL↗

arXiv2020

Moral Framing and Ideological Bias of News

News outlets are a primary source for many people to learn what is going on in the world. However, outlets with different political slants, when talking about the same news story, usually emphasize various aspects and choose their language framing differently. This framing implicitly shows their biases and also affects the reader's opinion and understanding. Therefore, understanding the framing in the news stories is fundamental for realizing what kind of view the writer is conveying with each news story. In this paper, we describe methods for characterizing moral frames in the news. We capture the frames based on the Moral Foundation Theory. This theory is a psychological concept which explains how every kind of morality and opinion can be summarized and presented with five main dimensions. We propose an unsupervised method that extracts the framing Bias and the framing Intensity without any external framing annotations provided. We validate the performance on an annotated twitter dataset and then use it to quantify the framing bias and partisanship of news.

cs.CY↗