Search

In this article we describe our experiences with computational text analysis involving rich social and cultural concepts. We hope to achieve three primary goals. First, we aim to shed light on thorny issues not always at the forefront of discussions about computational text analysis methods. Second, we hope to provide a set of key questions that can guide work in this area. Our guidance is based on our own experiences and is therefore inherently imperfect. Still, given our diversity of disciplinary backgrounds and research practices, we hope to capture a range of ideas and identify commonalities that resonate for many. This leads to our final goal: to help promote interdisciplinary collaborations. Interdisciplinary insights and partnerships are essential for realizing the full potential of any computational text analysis involving social and cultural concepts, and the more we bridge these divides, the more fruitful we believe our work will be., (Copyright © 2020 Nguyen, Liakata, DeDeo, Eisenstein, Mimno, Tromble and Winters.)

Exposure to frequent crime incidents has been found to have a negative bearing on the well-being of city residents, even if they are not themselves a direct victim. We pursue the research question of whether naturalistic data shared on Twitter may provide a "lens" to understand changes in psychological attributes of urban communities (1) immediately following crime incidents, as well as (2) due to long-term exposure to crime. We analyze half a million Twitter posts from the City of Atlanta in 2014, where the rate of violent crime is three times of the national average. In a first study, we develop a statistical method to detect changes in social media psychological attributes in the immediate aftermath of a crime event. Second, we develop a regression model that uses historical (yearlong) crime to predict Twitter negative emotion, anxiety, anger, and sadness. We do not find significant changes in social media affect immediately following crime in Atlanta. However we do observe significant ability of historical crime to account for heightened negative emotion and anger in the future. Our findings have implications in gauging the utility of social media to infer longitudinal and population-scale patterns of urban well-being.

Computer-mediated communication is driving fundamental changes in the nature of written language. We investigate these changes by statistical analysis of a dataset comprising 107 million Twitter messages (authored by 2.7 million unique user accounts). Using a latent vector autoregressive model to aggregate across thousands of words, we identify high-level patterns in diffusion of linguistic change over the United States. Our model is robust to unpredictable changes in Twitter's sampling rate, and provides a probabilistic characterization of the relationship of macro-scale linguistic influence to a set of demographic and geographic predictors. The results of this analysis offer support for prior arguments that focus on geographical proximity and population size. However, demographic similarity - especially with regard to race - plays an even more central role, as cities with similar racial demographics are far more likely to share linguistic influence. Rather than moving towards a single unified "netspeak" dialect, language evolution in computer-mediated communication reproduces existing fault lines in spoken American English.