Word embeddings are a powerful machine-learning framework that represents each English word by a vector. The geometric relationship between these vectors captures meaningful semantic relationships between the corresponding words. In this paper, we develop a framework to demonstrate how the temporal dynamics of the embedding helps to quantify changes in stereotypes and attitudes toward women and ethnic minorities in the 20th and 21st centuries in the United States. We integrate word embeddings trained on 100 y of text data with the US Census to show that changes in the embedding track closely with demographic and occupation shifts over time. The embedding captures societal shifts-e.g., the women's movement in the 1960s and Asian immigration into the United States-and also illuminates how specific adjectives and occupations became more closely associated with certain populations over time. Our framework for temporal analysis of word embedding opens up a fruitful intersection between machine learning and quantitative social science.

We provide an NLP framework to uncover four linguistic dimensions of political polarization in social media: topic choice, framing, affect and illocutionary force. We quantify these aspects with existing lexical methods, and propose clustering of tweet embeddings as a means to identify salient topics for analysis across events; human evaluations show that our approach generates more cohesive topics than traditional LDA-based models. We apply our methods to study 4.4M tweets on 21 mass shootings. We provide evidence that the discussion of these events is highly polarized politically and that this polarization is primarily driven by partisan differences in framing rather than topic choice. We identify framing devices, such as grounding and the contrasting use of the terms "terrorist" and "crazy", that contribute to polarization. Results pertaining to topic choice, affect and illocutionary force suggest that Republicans focus more on the shooter and event-specific facts (news) while Democrats focus more on the victims and call for policy changes. Our work contributes to a deeper understanding of the way group divisions manifest in language and to computational methods for studying them. 1

We study the problem of personalized, interactive tag recommendation for Flickr: While a user enters/selects new tags for a particular picture, the system suggests related tags to her, based on the tags that she or other people have used in the past along with (some of) the tags already entered. The suggested tags are dynamically updated with every additional tag entered/selected. We describe a new algorithm, called Hybrid, which can be applied to this problem, and show that it outperforms previous algorithms. It has only a single tunable parameter, which we found to be very robust.Apart from this new algorithm and its detailed analysis, our main contributions are (i) a clean methodology which leads to conservative performance estimates, (ii) showing how classical classification algorithms can be applied to this problem, (iii) introducing a new cost measure, which captures the effort of the whole tagging process, (iv) clearly identifying, when purely local schemes (using only a user's tagging history) can or cannot be improved by global schemes (using everybody's tagging history).

The University of California recently suspended through 2024 the requirement that California applicants submit SAT scores, upending the major role standardized testing has played in college admissions. We study the impact of this decision and its interplay with other policies-such as affirmative action-on admitted class composition.We develop a market model with schools and students. Students have an unobserved true skill level, a potentially observed demographic group membership, and an observed application with both test scores and other features. Bayesian schools optimize the dual-objectives of admitting (1) the "most qualified" and (2) a "diverse" cohort. They estimate each applicant's true skill level using the observed features and potentially their group membership, and then admit students with or without affirmative action.We show that dropping test scores may exacerbate disparities by decreasing the amount of information available for each applicant. However, if there are substantial barriers to testing, removing the test improves both academic merit and diversity by increasing the size of the applicant pool. We also find that affirmative action alongside using group membership in skill estimation is an effective strategy with respect to the dual-objective. Findings are validated with calibrated simulations using cross-national testing data.

Public and private institutions must often allocate scarce resources under uncertainty. Banks, for example, extend credit to loan applicants based in part on their estimated likelihood of repaying a loan.But when the quality of information differs across candidates (e.g., if some applicants lack traditional credit histories), common lending strategies can lead to disparities across groups. Here we consider a setting in which decision makers-before allocating resources-can choose to spend some of their limited budget further screening select individuals. We present a computationally efficient algorithm for deciding whom to screen that maximizes a standard measure of social welfare. Intuitively, decision makers should screen candidates on the margin, for whom the additional information could plausibly alter the allocation. We formalize this idea by showing the problem can be reduced to solving a series of linear programs. Both on synthetic and real-world datasets, this strategy improves utility, illustrating the value of targeted information acquisition in such decisions. Further, when there is social value for distributing resources to groups for whom we have a priori poor informationlike those without credit scores-our approach can substantially improve the allocation of limited assets.