Predicting stress in first-year college students using sleep data from wearable devices.

Consumer wearables have been successful at measuring sleep and may be useful in predicting changes in mental health measures such as stress. A key challenge remains in quantifying the relationship between sleep measures associated with physiologic stress and a user's experience of stress. Students from a public university enrolled in the Lived Experiences Measured Using Rings Study (LEMURS) provided continuous biometric data and answered weekly surveys during their first semester of college between October-December 2022. We analyzed weekly associations between estimated sleep measures and perceived stress for participants (N = 525). Through mixed-effects regression models, we identified consistent associations between perceived stress scores and average nightly total sleep time (TST), resting heart rate (RHR), heart rate variability (HRV), and respiratory rate (ARR). These effects persisted after controlling for gender and week of the semester. Specifically, for every additional hour of TST, the odds of experiencing moderate-to-high stress decreased by 0.617 or by 38.3% (p<0.01). For each 1 beat per minute increase in RHR, the odds of experiencing moderate-to-high stress increased by 1.036 or by 3.6% (p<0.01). For each 1 millisecond increase in HRV, the odds of experiencing moderate-to-high stress decreased by 0.988 or by 1.2% (p<0.05). For each additional breath per minute increase in ARR, the odds of experiencing moderate-to-high stress increased by 1.230 or by 23.0% (p<0.01). Consistent with previous research, participants who did not identify as male (i.e., female, nonbinary, and transgender participants) had significantly higher self-reported stress throughout the study. The week of the semester was also a significant predictor of stress. Sleep data from wearable devices may help us understand and to better predict stress, a strong signal of the ongoing mental health epidemic among college students.

A large clinical trial to improve well-being during the transition to college using wearables: The lived experiences measured using rings study.

INTRODUCTION: The transition to college is a period of elevated risk for a range of mental health conditions. Although colleges and universities strive to provide mental health support to their students, the high demand for these services makes it difficult to provide scalable, cost-effective solutions. OBJECTIVE: To address these issues, the present study aims to compare the efficacy of three different treatments using a large cohort of 600 students transitioning to college. Interventions were selected based on their potential for generalizability and cost-effectiveness on college campuses. METHODS: The study is a Phase II parallel-group, four-arm, randomized controlled trial with 1:1 allocation that will assign 600 participants to one (n = 150 per condition) of four arms: 1) group-based therapy, 2) physical activity program, 3) nature experiences, or 4) weekly assessment condition as a control group. Physiological data will be collected from all participants using a wearable device to develop algorithmic mental and physical health functioning predictions. Once recruitment is complete, modeling strategies will be used to evaluate the outcomes and effectiveness of each intervention. DISCUSSION: The findings of this study will provide evidence as to the benefits of implementing scalable and proactive interventions using technology with the goal of improving the well-being and success of new college students.

Say their names: Resurgence in the collective attention toward Black victims of fatal police violence following the death of George Floyd.

The murder of George Floyd by police in May 2020 sparked international protests and brought unparalleled levels of attention to the Black Lives Matter movement. As we show, his death set record levels of activity and amplification on Twitter, prompted the saddest day in the platform's history, and caused his name to appear among the ten most frequently used phrases in a day, where he is the only individual to have ever received that level of attention who was not known to the public earlier that same week. Importantly, we find that the Black Lives Matter movement's rhetorical strategy to connect and repeat the names of past Black victims of police violence-foregrounding racial injustice as an ongoing pattern rather than a singular event-was exceptionally effective following George Floyd's death: attention given to him extended to over 185 prior Black victims, more than other past moments in the movement's history. We contextualize this rising tide of attention among 12 years of racial justice activism on Twitter, demonstrating how activists and allies have used attention and amplification as a recurring tactic to lift and memorialize the names of Black victims of police violence. Our results show how the Black Lives Matter movement uses social media to center past instances of police violence at an unprecedented scale and speed, while still advancing the racial justice movement's longstanding goal to "say their names."

Quantifying Changes in the Language Used Around Mental Health on Twitter Over 10 Years: Observational Study.

BACKGROUND: Mental health challenges are thought to affect approximately 10% of the global population each year, with many of those affected going untreated because of the stigma and limited access to services. As social media lowers the barrier for joining difficult conversations and finding supportive groups, Twitter is an open source of language data describing the changing experience of a stigmatized group. OBJECTIVE: By measuring changes in the conversation around mental health on Twitter, we aim to quantify the hypothesized increase in discussions and awareness of the topic as well as the corresponding reduction in stigma around mental health. METHODS: We explored trends in words and phrases related to mental health through a collection of 1-, 2-, and 3-grams parsed from a data stream of approximately 10% of all English tweets from 2010 to 2021. We examined temporal dynamics of mental health language and measured levels of positivity of the messages. Finally, we used the ratio of original tweets to retweets to quantify the fraction of appearances of mental health language that was due to social amplification. RESULTS: We found that the popularity of the phrase mental health increased by nearly two orders of magnitude between 2012 and 2018. We observed that mentions of mental health spiked annually and reliably because of mental health awareness campaigns as well as unpredictably in response to mass shootings, celebrities dying by suicide, and popular fictional television stories portraying suicide. We found that the level of positivity of messages containing mental health, while stable through the growth period, has declined recently. Finally, we observed that since 2015, mentions of mental health have become increasingly due to retweets, suggesting that the stigma associated with the discussion of mental health on Twitter has diminished with time. CONCLUSIONS: These results provide useful texture regarding the growing conversation around mental health on Twitter and suggest that more awareness and acceptance has been brought to the topic compared with past years.

Gauging the happiness benefit of US urban parks through Twitter.

The relationship between nature contact and mental well-being has received increasing attention in recent years. While a body of evidence has accumulated demonstrating a positive relationship between time in nature and mental well-being, there have been few studies comparing this relationship in different locations over long periods of time. In this study, we analyze over 1.5 million tweets to estimate a happiness benefit, the difference in expressed happiness between in- and out-of-park tweets, for the 25 largest cities in the US by population. People write happier words during park visits when compared with non-park user tweets collected around the same time. While the words people write are happier in parks on average and in most cities, we find considerable variation across cities. Tweets are happier in parks at all times of the day, week, and year, not just during the weekend or summer vacation. Across all cities, we find that the happiness benefit is highest in parks larger than 100 acres. Overall, our study suggests the happiness benefit associated with park visitation is on par with US holidays such as Thanksgiving and New Year's Day.

Doomscrolling during COVID-19: The negative association between daily social and traditional media consumption and mental health symptoms during the COVID-19 pandemic.

OBJECTIVE: Consumption of traditional and social media markedly increased at the start of the COVID-19 pandemic as new information about the virus and safety guidelines evolved. Much of the information concerned restrictions on daily living activities and the risk posed by the virus. The term doomscrolling is used to describe the phenomenon of elevated negative affect after viewing pandemic-related media. The magnitude and duration of this effect, however, is unclear. Furthermore, the effect of doomscrolling likely varies based on prior vulnerabilities for psychopathology, such as a history of childhood maltreatment. It was hypothesized that social and traditional media exposure were related to an increase in depression and PTSD and that this increase was moderated by childhood maltreatment severity. METHOD: Participants completed a baseline assessment for psychopathology and 30 days of daily assessments of depression, PTSD, and pandemic-related media use. RESULTS: Using multilevel modeling, social media exposure was associated with increased depression and PTSD. This association was stronger for those with more severe maltreatment histories. Furthermore, those with more severe baseline psychopathology used more social media during this period. These relations were not observed for traditional media sources. CONCLUSIONS: These results suggest that regular viewing of pandemic-related social media is associated with increases in psychopathology for those with existing vulnerabilities. Those with such vulnerabilities should adopt strategies to limit social media consumption. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Spatial changes in park visitation at the onset of the pandemic.

The COVID-19 pandemic disrupted the mobility patterns of a majority of Americans beginning in March 2020. Despite the beneficial, socially distanced activity offered by outdoor recreation, confusing and contradictory public health messaging complicated access to natural spaces. Working with a dataset comprising the locations of roughly 50 million distinct mobile devices in 2019 and 2020, we analyze weekly visitation patterns for 8,135 parks across the United States. Using Bayesian inference, we identify regions that experienced a substantial change in visitation in the first few weeks of the pandemic. We find that regions that did not exhibit a change were likely to have smaller populations, and to have voted more republican than democrat in the 2020 elections. Our study contributes to a growing body of literature using passive observations to explore who benefits from access to nature.

Computational timeline reconstruction of the stories surrounding Trump: Story turbulence, narrative control, and collective chronopathy.

Measuring the specific kind, temporal ordering, diversity, and turnover rate of stories surrounding any given subject is essential to developing a complete reckoning of that subject's historical impact. Here, we use Twitter as a distributed news and opinion aggregation source to identify and track the dynamics of the dominant day-scale stories around Donald Trump, the 45th President of the United States. Working with a data set comprising around 20 billion 1-grams, we first compare each day's 1-gram and 2-gram usage frequencies to those of a year before, to create day- and week-scale timelines for Trump stories for 2016-2021. We measure Trump's narrative control, the extent to which stories have been about Trump or put forward by Trump. We then quantify story turbulence and collective chronopathy-the rate at which a population's stories for a subject seem to change over time. We show that 2017 was the most turbulent overall year for Trump. In 2020, story generation slowed dramatically during the first two major waves of the COVID-19 pandemic, with rapid turnover returning first with the Black Lives Matter protests following George Floyd's murder and then later by events leading up to and following the 2020 US presidential election, including the storming of the US Capitol six days into 2021. Trump story turnover for 2 months during the COVID-19 pandemic was on par with that of 3 days in September 2017. Our methods may be applied to any well-discussed phenomenon, and have potential to enable the computational aspects of journalism, history, and biography.

Storywrangler: A massive exploratorium for sociolinguistic, cultural, socioeconomic, and political timelines using Twitter.

In real time, Twitter strongly imprints world events, popular culture, and the day-to-day, recording an ever-growing compendium of language change. Vitally, and absent from many standard corpora such as books and news archives, Twitter also encodes popularity and spreading through retweets. Here, we describe Storywrangler, an ongoing curation of over 100 billion tweets containing 1 trillion 1-grams from 2008 to 2021. For each day, we break tweets into 1-, 2-, and 3-grams across 100+ languages, generating frequencies for words, hashtags, handles, numerals, symbols, and emojis. We make the dataset available through an interactive time series viewer and as downloadable time series and daily distributions. Although Storywrangler leverages Twitter data, our method of tracking dynamic changes in n-grams can be extended to any temporally evolving corpus. Illustrating the instrument's potential, we present example use cases including social amplification, the sociotechnical dynamics of famous individuals, box office success, and social unrest.

Local information sources received the most attention from Puerto Ricans during the aftermath of Hurricane Maria.

In September 2017, Hurricane Maria made landfall across the Caribbean region as a category 4 storm. In the aftermath, many residents of Puerto Rico were without power or clean running water for nearly a year. Using both English and Spanish tweets from September 16 to October 15 2017, we investigate discussion of Maria both on and off the island, constructing a proxy for the temporal network of communication between victims of the hurricane and others. We use information theoretic tools to compare the lexical divergence of different subgroups within the network. Lastly, we quantify temporal changes in user prominence throughout the event. We find at the global level that Spanish tweets more often contained messages of hope and a focus on those helping. At the local level, we find that information propagating among Puerto Ricans most often originated from sources local to the island, such as journalists and politicians. Critically, content from these accounts overshadows content from celebrities, global news networks, and the like for the large majority of the time period studied. Our findings reveal insight into ways social media campaigns could be deployed to disseminate relief information during similar events in the future.

Hurricanes and hashtags: Characterizing online collective attention for natural disasters.

We study collective attention paid towards hurricanes through the lens of n-grams on Twitter, a social media platform with global reach. Using hurricane name mentions as a proxy for awareness, we find that the exogenous temporal dynamics are remarkably similar across storms, but that overall collective attention varies widely even among storms causing comparable deaths and damage. We construct 'hurricane attention maps' and observe that hurricanes causing deaths on (or economic damage to) the continental United States generate substantially more attention in English language tweets than those that do not. We find that a hurricane's Saffir-Simpson wind scale category assignment is strongly associated with the amount of attention it receives. Higher category storms receive higher proportional increases of attention per proportional increases in number of deaths or dollars of damage, than lower category storms. The most damaging and deadly storms of the 2010s, Hurricanes Harvey and Maria, generated the most attention and were remembered the longest, respectively. On average, a category 5 storm receives 4.6 times more attention than a category 1 storm causing the same number of deaths and economic damage.

The growing amplification of social media: measuring temporal and social contagion dynamics for over 150 languages on Twitter for 2009-2020.

Working from a dataset of 118 billion messages running from the start of 2009 to the end of 2019, we identify and explore the relative daily use of over 150 languages on Twitter. We find that eight languages comprise 80% of all tweets, with English, Japanese, Spanish, Arabic, and Portuguese being the most dominant. To quantify social spreading in each language over time, we compute the 'contagion ratio': The balance of retweets to organic messages. We find that for the most common languages on Twitter there is a growing tendency, though not universal, to retweet rather than share new content. By the end of 2019, the contagion ratios for half of the top 30 languages, including English and Spanish, had reached above 1-the naive contagion threshold. In 2019, the top 5 languages with the highest average daily ratios were, in order, Thai (7.3), Hindi, Tamil, Urdu, and Catalan, while the bottom 5 were Russian, Swedish, Esperanto, Cebuano, and Finnish (0.26). Further, we show that over time, the contagion ratios for most common languages are growing more strongly than those of rare languages.

Ratioing the President: An exploration of public engagement with Obama and Trump on Twitter.

The past decade has witnessed a marked increase in the use of social media by politicians, most notably exemplified by the 45th President of the United States (POTUS), Donald Trump. On Twitter, POTUS messages consistently attract high levels of engagement as measured by likes, retweets, and replies. Here, we quantify the balance of these activities, also known as "ratios", and study their dynamics as a proxy for collective political engagement in response to presidential communications. We find that raw activity counts increase during the period leading up to the 2016 election, accompanied by a regime change in the ratio of retweets-to-replies connected to the transition between campaigning and governing. For the Trump account, we find words related to fake news and the Mueller inquiry are more common in tweets with a high number of replies relative to retweets. Finally, we find that Barack Obama consistently received a higher retweet-to-reply ratio than Donald Trump. These results suggest Trump's Twitter posts are more often controversial and subject to enduring engagement as a given news cycle unfolds.

How the world's collective attention is being paid to a pandemic: COVID-19 related n-gram time series for 24 languages on Twitter.

In confronting the global spread of the coronavirus disease COVID-19 pandemic we must have coordinated medical, operational, and political responses. In all efforts, data is crucial. Fundamentally, and in the possible absence of a vaccine for 12 to 18 months, we need universal, well-documented testing for both the presence of the disease as well as confirmed recovery through serological tests for antibodies, and we need to track major socioeconomic indices. But we also need auxiliary data of all kinds, including data related to how populations are talking about the unfolding pandemic through news and stories. To in part help on the social media side, we curate a set of 2000 day-scale time series of 1- and 2-grams across 24 languages on Twitter that are most 'important' for April 2020 with respect to April 2019. We determine importance through our allotaxonometric instrument, rank-turbulence divergence. We make some basic observations about some of the time series, including a comparison to numbers of confirmed deaths due to COVID-19 over time. We broadly observe across all languages a peak for the language-specific word for 'virus' in January 2020 followed by a decline through February and then a surge through March and April. The world's collective attention dropped away while the virus spread out from China. We host the time series on Gitlab, updating them on a daily basis while relevant. Our main intent is for other researchers to use these time series to enhance whatever analyses that may be of use during the pandemic as well as for retrospective investigations.

Augmenting Semantic Lexicons Using Word Embeddings and Transfer Learning.

Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based and contextual. Although recent contextual models are increasingly dominant, we still see demand for lexicon-based models because of their interpretability and ease of use. For example, lexicon-based models allow researchers to readily determine which words and phrases contribute most to a change in measured sentiment. A challenge for any lexicon-based approach is that the lexicon needs to be routinely expanded with new words and expressions. Here, we propose two models for automatic lexicon expansion. Our first model establishes a baseline employing a simple and shallow neural network initialized with pre-trained word embeddings using a non-contextual approach. Our second model improves upon our baseline, featuring a deep Transformer-based network that brings to bear word definitions to estimate their lexical polarity. Our evaluation shows that both models are able to score new words with a similar accuracy to reviewers from Amazon Mechanical Turk, but at a fraction of the cost.

Hahahahaha, Duuuuude, Yeeessss!: A two-parameter characterization of stretchable words and the dynamics of mistypings and misspellings.

Stretched words like 'heellllp' or 'heyyyyy' are a regular feature of spoken language, often used to emphasize or exaggerate the underlying meaning of the root word. While stretched words are rarely found in formal written language and dictionaries, they are prevalent within social media. In this paper, we examine the frequency distributions of 'stretchable words' found in roughly 100 billion tweets authored over an 8 year period. We introduce two central parameters, 'balance' and 'stretch', that capture their main characteristics, and explore their dynamics by creating visual tools we call 'balance plots' and 'spelling trees'. We discuss how the tools and methods we develop here could be used to study the statistical patterns of mistypings and misspellings and be used as a basis for other linguistic research involving stretchable words, along with the potential applications in augmenting dictionaries, improving language processing, and in any area where sequence construction matters, such as genetics.

Noncooperative dynamics in election interference.

Foreign power interference in domestic elections is an existential threat to societies. Manifested through myriad methods from war to words, such interference is a timely example of strategic interaction between economic and political agents. We model this interaction between rational game players as a continuous-time differential game, constructing an analytical model of this competition with a variety of payoff structures. All-or-nothing attitudes by only one player regarding the outcome of the game lead to an arms race in which both countries spend increasing amounts on interference and counterinterference operations. We then confront our model with data pertaining to the Russian interference in the 2016 United States presidential election contest. We introduce and estimate a Bayesian structural time-series model of election polls and social media posts by Russian Twitter troll accounts. Our analytical model, while purposefully abstract and simple, adequately captures many temporal characteristics of the election and social media activity. We close with a discussion of our model's shortcomings and suggestions for future research.

Social media usage patterns during natural hazards.

Natural hazards are becoming increasingly expensive as climate change and development are exposing communities to greater risks. Preparation and recovery are critical for climate change resilience, and social media are being used more and more to communicate before, during, and after disasters. While there is a growing body of research aimed at understanding how people use social media surrounding disaster events, most existing work has focused on a single disaster case study. In the present study, we analyze five of the costliest disasters in the last decade in the United States (Hurricanes Irene and Sandy, two sets of tornado outbreaks, and flooding in Louisiana) through the lens of Twitter. In particular, we explore the frequency of both generic and specific food-security related terms, and quantify the relationship between network size and Twitter activity during disasters. We find differences in tweet volume for keywords depending on disaster type, with people using Twitter more frequently in preparation for Hurricanes, and for real-time or recovery information for tornado and flooding events. Further, we find that people share a host of general disaster and specific preparation and recovery terms during these events. Finally, we find that among all account types, individuals with "average" sized networks are most likely to share information during these disasters, and in most cases, do so more frequently than normal. This suggests that around disasters, an ideal form of social contagion is being engaged in which average people rather than outsized influentials are key to communication. These results provide important context for the type of disaster information and target audiences that may be most useful for disaster communication during varying extreme events.

English verb regularization in books and tweets.

The English language has evolved dramatically throughout its lifespan, to the extent that a modern speaker of Old English would be incomprehensible without translation. One concrete indicator of this process is the movement from irregular to regular (-ed) forms for the past tense of verbs. In this study we quantify the extent of verb regularization using two vastly disparate datasets: (1) Six years of published books scanned by Google (2003-2008), and (2) A decade of social media messages posted to Twitter (2008-2017). We find that the extent of verb regularization is greater on Twitter, taken as a whole, than in English Fiction books. Regularization is also greater for tweets geotagged in the United States relative to American English books, but the opposite is true for tweets geotagged in the United Kingdom relative to British English books. We also find interesting regional variations in regularization across counties in the United States. However, once differences in population are accounted for, we do not identify strong correlations with socio-demographic variables such as education or income.

Continuum rich-get-richer processes: Mean field analysis with an application to firm size.

Classical rich-get-richer models have found much success in being able to broadly reproduce the statistics and dynamics of diverse real complex systems. These rich-get-richer models are based on classical urn models and unfold step by step in discrete time. Here, we consider a natural variation acting on a temporal continuum in the form of a partial differential equation (PDE). We first show that the continuum version of Simon's canonical preferential attachment model exhibits an identical size distribution. In relaxing Simon's assumption of a linear growth mechanism, we consider the case of an arbitrary growth kernel and find the general solution to the resultant PDE. We then extend the PDE to multiple spatial dimensions, again determining the general solution. We then relax the zero-diffusion assumption and find an envelope of solutions to the general model in the presence of small fluctuations. Finally, we apply the model to size and wealth distributions of firms. We obtain power-law scaling for both to be concordant with simulations as well as observational data, providing a parsimonious theoretical explanation for these phenomena.