The risk of racial bias while tracking influenza-related content on social media using machine learning

Natural language model for automatic identification of Intimate Partner Violence reports from Twitter

Intimate partner violence (IPV) is a preventable public health problem that affects millions of people worldwide. Approximately one in four women are estimated to be or have been victims of severe violence at some point in their lives, irrespective of age, ethnicity, and economic status. Victims often report IPV experiences on social media, and automatic detection of such reports via machine learning may enable improved surveillance and targeted distribution of support and/or interventions for those in need. However, no artificial intelligence systems for automatic detection currently exists, and we attempted to address this research gap. We collected posts from Twitter using a list of IPV-related keywords, manually reviewed subsets of retrieved posts, and prepared annotation guidelines to categorize tweets into IPV-report or non-IPV-report. We annotated 6,348 tweets in total, with the inter-annotator agreement (IAA) of 0.86 (Cohen's kappa) among 1,834 double-annotated tweets. The class distribution in the annotated dataset was highly imbalanced, with only 668 posts (~11%) labeled as IPV-report. We then developed an effective natural language processing model to identify IPV-reporting tweets automatically. The developed model achieved classification F₁-scores of 0.76 for the IPV-report class and 0.97 for the non-IPV-report class. We conducted post-classification analyses to determine the causes of system errors and to ensure that the system did not exhibit biases in its decision making, particularly with respect to race and gender. Our automatic model can be an essential component for a proactive social media-based intervention and support framework, while also aiding population-level surveillance and large-scale cohort studies.

Statistical quantification of confounding bias in machine learning models

BACKGROUND

The lack of nonparametric statistical tests for confounding bias significantly hampers the development of robust, valid, and generalizable predictive models in many fields of research. Here I propose the partial confounder test, which, for a given confounder variable, probes the null hypotheses of the model being unconfounded.

RESULTS

The test provides a strict control for type I errors and high statistical power, even for nonnormally and nonlinearly dependent predictions, often seen in machine learning. Applying the proposed test on models trained on large-scale functional brain connectivity data (N= 1,865) (i) reveals previously unreported confounders and (ii) shows that state-of-the-art confound mitigation approaches may fail preventing confounder bias in several cases.

CONCLUSIONS

The proposed test (implemented in the package mlconfound; https://mlconfound.readthedocs.io) can aid the assessment and improvement of the generalizability and validity of predictive models and, thereby, fosters the development of clinically useful machine learning biomarkers.

Best Practices on Big Data Analytics to Address Sex-Specific Biases in Our Understanding of the Etiology, Diagnosis, and Prognosis of Diseases

A bias in health research to favor understanding diseases as they present in men can have a grave impact on the health of women. This paper reports on a conceptual review of the literature on machine learning or natural language processing (NLP) techniques to interrogate big data for identifying sex-specific health disparities. We searched Ovid MEDLINE, Embase, and PsycINFO in October 2021 using synonyms and indexing terms for (a) "women," "men," or "sex"; (b) "big data," "artificial intelligence," or "NLP"; and (c) "disparities" or "differences." From 902 records, 22 studies met the inclusion criteria and were analyzed. Results demonstrate that the inclusion by sex is inconsistent and often unreported, although the inclusion of men in these studies is disproportionately less than women. Even though artificial intelligence and NLP techniques are widely applied in healthresearch, few studies use them to take advantage of unstructured text to investigate sex-related differences or disparities. Researchers are increasingly aware of sex-based data bias, but the process toward correction is slow. We reflect on best practices on using big data analytics to address sex-specific biases in understanding the etiology, diagnosis, and prognosis of diseases.

Methods to Establish Race or Ethnicity of Twitter Users: Scoping Review

Background

A growing amount of health research uses social media data. Those critical of social media research often cite that it may be unrepresentative of the population; however, the suitability of social media data in digital epidemiology is more nuanced. Identifying the demographics of social media users can help establish representativeness.

Objective

This study aims to identify the different approaches or combination of approaches to extract race or ethnicity from social media and report on the challenges of using these methods.

Methods

We present a scoping review to identify methods used to extract the race or ethnicity of Twitter users from Twitter data sets. We searched 17 electronic databases from the date of inception to May 15, 2021, and carried out reference checking and hand searching to identify relevant studies. Sifting of each record was performed independently by at least two researchers, with any disagreement discussed. Studies were required to extract the race or ethnicity of Twitter users using either manual or computational methods or a combination of both.

Results

Of the 1249 records sifted, we identified 67 (5.36%) that met our inclusion criteria. Most studies (51/67, 76%) have focused on US-based users and English language tweets (52/67, 78%). A range of data was used, including Twitter profile metadata, such as names, pictures, information from bios (including self-declarations), or location or content of the tweets. A range of methodologies was used, including manual inference, linkage to census data, commercial software, language or dialect recognition, or machine learning or natural language processing. However, not all studies have evaluated these methods. Those that evaluated these methods found accuracy to vary from 45% to 93% with significantly lower accuracy in identifying categories of people of color. The inference of race or ethnicity raises important ethical questions, which can be exacerbated by the data and methods used. The comparative accuracies of the different methods are also largely unknown.

Conclusions

There is no standard accepted approach or current guidelines for extracting or inferring the race or ethnicity of Twitter users. Social media researchers must carefully interpret race or ethnicity and not overpromise what can be achieved, as even manual screening is a subjective, imperfect method. Future research should establish the accuracy of methods to inform evidence-based best practice guidelines for social media researchers and be guided by concerns of equity and social justice.