Demographic Representation and Collective Storytelling in the Me Too Twitter Hashtag Activism Movement

The #MeToo movement on Twitter has drawn attention to the pervasive nature of sexual harassment and violence. While #MeToo has been praised for providing support for self-disclosures of harassment or violence and shifting societal response, it has also been criticized for exemplifying how women of color have been discounted for their historical contributions to and excluded from feminist movements. Through an analysis of over 600,000 tweets from over 256,000 unique users, we examine online #MeToo conversations across gender and racial/ethnic identities and the topics that each demographic emphasized. We found that tweets authored by white women were overrepresented in the movement compared to other demographics, aligning with criticism of unequal representation. We found that intersected identities contributed differing narratives to frame the movement, co-opted the movement to raise visibility in parallel ongoing movements, employed the same hashtags both critically and supportively, and revived and created new hashtags in response to pivotal moments. Notably, tweets authored by black women often expressed emotional support and were critical about differential treatment in the justice system and by police. In comparison, tweets authored by white women and men often highlighted sexual harassment and violence by public figures and weaved in more general political discussions. We discuss the implications of this work for digital activism research and design, including suggestions to raise visibility by those who were under-represented in this hashtag activism movement. Content warning: this article discusses issues of sexual harassment and violence.

Leveraging Machine Learning to Predict 30-Day Hospital Readmission after Cardiac Surgery

BACKGROUND

Hospital readmission within 30 days of discharge is a well-studied outcome. Predicting readmission after cardiac surgery, however, is notoriously challenging; the best-performing models in the literature have AUCs around .65. A reliable predictive model would enable clinicians to identify patients at-risk for readmission and develop prevention strategies.

METHODS

We analyzed our institution's STS Adult Cardiac Surgery Database (STS), augmented with electronic medical record (EMR) data. Predictors included demographics, pre-operative comorbidities, proxies for intra-operative risk, indicators of post-operative complications, and timeseries-derived variables. We trained several machine learning models, evaluating each on a held-out test set.

RESULTS

Our analysis cohort consisted of 4,924 cases from 2011-2016. 723 (14.7%) were readmitted within 30 days of discharge. Our models included 141 STS-derived and 24 EMR-derived variables. A random forest model performed best, with test AUC .76 (95% CI: (.73, .79)). Using exclusively pre-operative variables, as in STS calculated risk scores, degraded the AUC: .64 (95% CI: .60, .68). Key predictors included length of stay (12.5x more important than the average variable) and whether the patient was discharged to a rehab facility (11.2x).

CONCLUSIONS

Our approach, augmenting STS variables with EMR data and employing flexible machine learning modeling, yielded state-of-the-art performance for predicting 30-day readmission. Separately, the importance of variables not directly related to in-patient care, such as discharge location, amplifies questions about the efficacy of assessing care quality via readmissions.

Vaccine-related advertising in the Facebook Ad Archive

BACKGROUND

In 2018, Facebook introduced Ad Archive as a platform to improve transparency in advertisements related to politics and "issues of national importance." Vaccine-related Facebook advertising is publicly available for the first time. After measles outbreaks in the US brought renewed attention to the possible role of Facebook advertising in the spread of vaccine-related misinformation, Facebook announced steps to limit vaccine-related misinformation. This study serves as a baseline of advertising before new policies went into effect.

METHODS

Using the keyword 'vaccine', we searched Ad Archive on December 13, 2018 and again on February 22, 2019. We exported data for 505 advertisements. A team of annotators sorted advertisements by content: pro-vaccine, anti-vaccine, not relevant. We also conducted a thematic analysis of major advertising themes. We ran Mann-Whitney U tests to compare ad performance metrics.

RESULTS

309 advertisements were included in analysis with 163 (53%) pro-vaccine advertisements and 145 (47%) anti-vaccine advertisements. Despite a similar number of advertisements, the median number of ads per buyer was significantly higher for anti-vaccine ads. First time buyers are less likely to complete disclosure information and risk ad removal. Thematically, anti-vaccine advertising messages are relatively uniform and emphasize vaccine harms (55%). In contrast, pro-vaccine advertisements come from a diverse set of buyers (83 unique) with varied goals including promoting vaccination (49%), vaccine related philanthropy (15%), and vaccine related policy (14%).

CONCLUSIONS

A small set of anti-vaccine advertisement buyers have leveraged Facebook advertisements to reach targeted audiences. By deeming all vaccine-related content an issue of "national importance," Facebook has further the politicized vaccines. The implementation of a blanket disclosure policy also limits which ads can successfully run on Facebook. Improving transparency and limiting misinformation should not be separate goals. Public health communication efforts should consider the potential impact on Facebook users' vaccine attitudes and behaviors.

Challenges of Using Text Classifiers for Causal Inference

Causal understanding is essential for many kinds of decision-making, but causal inference from observational data has typically only been applied to structured, low-dimensional datasets. While text classifiers produce low-dimensional outputs, their use in causal inference has not previously been studied. To facilitate causal analyses based on language data, we consider the role that text classifiers can play in causal inference through established modeling mechanisms from the causality literature on missing data and measurement error. We demonstrate how to conduct causal analyses using text classifiers on simulated and Yelp data, and discuss the opportunities and challenges of future work that uses text data in causal inference.