Abstract
We comment on Eichstaedt et al.’s (2015a) claim to have shown that language patterns among Twitter users, aggregated at the level of US counties, predicted county-level mortality rates from atherosclerotic heart disease (AHD), with “negative” language being associated with higher rates of death from AHD and “positive” language associated with lower rates. First, we examine some of Eichstaedt et al.’s apparent assumptions about the nature of AHD, as well as some issues related to the secondary analysis of online data and to considering counties as communities. Next, using the data files supplied by Eichstaedt et al., we reproduce their regression- and correlation-based models, substituting mortality from an alternative cause of death—namely, suicide—as the outcome variable, and observe that the purported associations between “negative” and “positive” language and mortality are reversed when suicide is used as the outcome variable. We identify numerous other conceptual and methodological limitations that call into question the robustness and generalizability of Eichstaedt et al.’s claims, even when these are based on the results of their ridge regression/machine learning model. We conclude that there is no good evidence that analyzing Twitter data in bulk in this way can add anything useful to our ability to understand geographical variation in AHD mortality rates.
Highlights
Eichstaedt et al (2015a) claimed to have demonstrated that language patterns among Twitter users, aggregated at the level of US counties, were predictive of mortality rates from atherosclerotic heart disease (AHD) in those counties, with ‘‘negative’’ language being associated with higher rates of death from AHD and ‘‘positive’’ language being associated with lower AHD mortality
Eichstaedt et al examined a variety of measures to demonstrate the associations between Twitter language patterns and AHD, including (a) the frequency of usage of individual words associated with either positive or negative feelings or behaviors, (b) the tendency of Twitter users to discuss ‘‘positive’’ or ‘‘negative’’ topics, and (c) an omnibus model incorporating all of their Twitter data, whose
[I]n New York County, New York, . . . neighborhoods range from the Upper East Side and SoHo to Harlem and Washington Heights. . . . [I]n San Mateo County, California, . . . neighborhoods range from the Woodside estates of Silicon Valley billionaires to the Redwood City bungalows of Mexican immigrants. (Abrams & Fiorina, 2012, p. 206). Given such diversity in the scale and sociopolitical significance of counties, we find it difficult to conceive of a county-level factor, or set of factors, that might be associated with both Twitter language and AHD prevalence with any degree of consistency across the United States
Summary
Eichstaedt et al (2015a) claimed to have demonstrated that language patterns among Twitter users, aggregated at the level of US counties, were predictive of mortality rates from atherosclerotic heart disease (AHD) in those counties, with ‘‘negative’’ language (expressing themes such as disengagement or negative relationships) being associated with higher rates of death from AHD and ‘‘positive’’ language (e.g., upbeat descriptions of social interactions or positive emotions) being associated with lower AHD mortality. A close examination of Eichstaedt et al.’s article and data appears to reveal a number of potential sources of distortion and bias in its assumptions about the nature of AHD, the use of Twitter data as a proxy for the socioemotional environment and people’s health, and the use of counties as the unit of analysis. Some of these problems are immediately obvious from reading Eichstaedt et al.’s article, while others only manifested themselves in the testing of the relevant data that we undertook
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
