Variation in social media sensitivity across people and contexts

Social media impacts people's wellbeing in different ways, but relatively little is known about why this is the case. Here we introduce the construct of "social media sensitivity" to understand how social media and wellbeing associations differ across people and the contexts in which these platforms are used. In a month-long large-scale intensive longitudinal study (total n = 1632; total number of observations = 120,599), we examined for whom and under which circumstances social media was associated with positive and negative changes in social and affective wellbeing. Applying a combination of frequentist and Bayesian multilevel models, we found a small negative average association between social media use AND subsequent wellbeing, but the associations were heterogenous across people. People with psychologically vulnerable dispositions (e.g., those who were depressed, lonely, not satisfied with life) tended to experience heightened negative social media sensitivity in comparison to people who were not psychologically vulnerable. People also experienced heightened negative social media sensitivity when in certain types of places (e.g., in social places, in nature) and while around certain types of people (e.g., around family members, close ties), as compared to using social media in other contexts. Our results suggest that an understanding of the effects of social media on wellbeing should account for the psychological dispositions of social media users, and the physical and social contexts surrounding their use. We discuss theoretical and practical implications of social media sensitivity for scholars, policymakers, and those in the technology industry.

The potential of generative AI for personalized persuasion at scale

Matching the language or content of a message to the psychological profile of its recipient (known as "personalized persuasion") is widely considered to be one of the most effective messaging strategies. We demonstrate that the rapid advances in large language models (LLMs), like ChatGPT, could accelerate this influence by making personalized persuasion scalable. Across four studies (consisting of seven sub-studies; total N = 1788), we show that personalized messages crafted by ChatGPT exhibit significantly more influence than non-personalized messages. This was true across different domains of persuasion (e.g., marketing of consumer products, political appeals for climate action), psychological profiles (e.g., personality traits, political ideology, moral foundations), and when only providing the LLM with a single, short prompt naming or describing the targeted psychological dimension. Thus, our findings are among the first to demonstrate the potential for LLMs to automate, and thereby scale, the use of personalized persuasion in ways that enhance its effectiveness and efficiency. We discuss the implications for researchers, practitioners, and the general public.

Situating smartphones in daily life: Big Five traits and contexts associated with young adults' smartphone use

We examine individual differences in smartphone behavior to understand the independent effects of Big Five traits and four different contextual factors (places, people, co-occurring activities, and psychological situations) on the frequency and duration of smartphone use in daily life. Using survey, experience sampling, and mobile sensing data collected over the span of 2 weeks from two samples of college students (Sample 1, N = 634; Sample 2, N = 211), we conducted a series of multilevel Bayesian gamma hurdle and negative binomial hurdle models to explain smartphone use (vs. nonuse) and the degree of use. Our pooled findings suggest that extraversion was associated with more frequent use, while conscientiousness was associated with smartphone nonuse and shorter durations of use. In terms of context, our findings show that smartphones were used more frequently when people were out and about in public places (e.g., cafes, stores) and less frequently in particularly social places (e.g., bars, friends' houses). Smartphones were also used more frequently with weak ties (e.g., classmates, coworkers) and less frequently with close ties (e.g., roommates, family, significant others). Smartphones were also used less and for shorter durations when people were engaged in certain activities (e.g., studying, commuting, chores, exercising), and when in situations perceived to be romantic or involving work. We discuss the findings with regard to past work on smartphone use and describe the next steps for research on smartphone behavior. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Well-being in social interactions: Examining personality-situation dynamics in face-to-face and computer-mediated communication

Decades of research show that people's social lives are linked to their well-being. Yet, research on the relationship between social interactions and well-being has been largely inconclusive with regard to the effects of person-situation interactions, such as the interplay between contextual factors (e.g., interactions occurring in physical vs. digital contexts, different interaction partners) and dispositional tendencies (e.g., Big Five personality traits). Here, we report on exploratory and confirmatory findings from three large studies of college students (Study 1: N = 1,360; Study 2: N = 851; Study 3: N = 864) who completed a total of 139,363 experience sampling surveys (reporting on 87,976 social interactions). We focus on the effects of different modes of communication (face-to-face [FtF] interactions, computer-mediated communication [CMC], and mixed episodes [FtF + CMC]), and types of interaction partners (close peers, family members, and weak ties). Using multilevel structural equation modeling, we found that FtF interactions and mixed episodes were associated with highest well-being on the within-person level, and that these effects were particularly pronounced for individuals with high levels of neuroticism. CMC was related to lower well-being than FtF interactions, but higher well-being than not socializing at all. Regarding the type of interaction partner, individuals reported higher well-being after interactions with close peers than after interactions with family members and weak ties, and the difference between close peers and weak ties was larger for FtF interactions than for CMC. We discuss these findings with regard to theories of person-situation interactions and research on well-being and social interactions. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Evaluating voice samples as a potential source of information about personality

Speech is a powerful medium through which a variety of psychologically relevant phenomena are expressed. Here we take a first step in evaluating the potential of using voice samples as non-self-report measures of personality. In particular, we examine the extent to which linguistic and vocal information extracted from semi-structured vocal samples can be used to predict conventional measures of personality. We extracted 94 linguistic features (using Linquistic Inquiry Word Count, 2015) and 272 vocal features (using pyAudioAnalysis) from 614 voice samples of at least 50 words. Using a two-stage, fully automatable machine learning pipeline we evaluated the extent to which these features predicted self-report personality scales (Big Five Inventory). For comparison purposes, we also examined the predictive performance of these voice features with respect to depression, age, and gender. Results showed that voice samples accounted for 10.67 % of the variance in personality traits on average and that the same samples could also predict depression, age, and gender. Moreover, the results reported here provide a conservative estimate of the degree to which features derived from voice samples could be used to predict personality traits and suggest a number of opportunities to optimize personality prediction and better understand how voice samples carry information about personality.

Analyzing GPS Data for Psychological Research: A Tutorial

The ubiquity of location-data-enabled devices provides novel avenues for psychology researchers to incorporate spatial analytics into their studies. Spatial analytics use global positioning system (GPS) data to assess and understand mobility behavior (e.g., locations visited, movement patterns). In this tutorial, we provide a practical guide to analyzing GPS data in R and introduce researchers to key procedures and resources for conducting spatial analytics. We show readers how to clean GPS data, compute mobility features (e.g., time spent at home, number of unique places visited), and visualize locations and movement patterns. In addition, we discuss the challenges of ensuring participant privacy and interpreting the psychological implications of mobility behaviors. The tutorial is accompanied by an R Markdown script and a simulated GPS data set made available on the OSF.

Multi-modal data collection for measuring health, behavior, and living environment of large-scale participant cohorts

BACKGROUND

As mobile technologies become ever more sensor-rich, portable, and ubiquitous, data captured by smart devices are lending rich insights into users' daily lives with unprecedented comprehensiveness and ecological validity. A number of human-subject studies have been conducted to examine the use of mobile sensing to uncover individual behavioral patterns and health outcomes, yet minimal attention has been placed on measuring living environments together with other human-centered sensing data. Moreover, the participant sample size in most existing studies falls well below a few hundred, leaving questions open about the reliability of findings on the relations between mobile sensing signals and human outcomes.

RESULTS

To address these limitations, we developed a home environment sensor kit for continuous indoor air quality tracking and deployed it in conjunction with smartphones, Fitbits, and ecological momentary assessments in a cohort study of up to 1,584 college student participants per data type for 3 weeks. We propose a conceptual framework that systematically organizes human-centric data modalities by their temporal coverage and spatial freedom. Then we report our study procedure, technologies and methods deployed, and descriptive statistics of the collected data that reflect the participants' mood, sleep, behavior, and living environment.

CONCLUSIONS

We were able to collect from a large participant cohort satisfactorily complete multi-modal sensing and survey data in terms of both data continuity and participant adherence. Our novel data and conceptual development provide important guidance for data collection and hypothesis generation in future human-centered sensing studies.

Personality Research and Assessment in the Era of Machine Learning

The increasing availability of high–dimensional, fine–grained data about human behaviour, gathered from mobile sensing studies and in the form of digital footprints, is poised to drastically alter the way personality psychologists perform research and undertake personality assessment. These new kinds and quantities of data raise important questions about how to analyse the data and interpret the results appropriately. Machine learning models are well suited to these kinds of data, allowing researchers to model highly complex relationships and to evaluate the generalizability and robustness of their results using resampling methods. The correct usage of machine learning models requires specialized methodological training that considers issues specific to this type of modelling. Here, we first provide a brief overview of past studies using machine learning in personality psychology. Second, we illustrate the main challenges that researchers face when building, interpreting, and validating machine learning models. Third, we discuss the evaluation of personality scales, derived using machine learning methods. Fourth, we highlight some key issues that arise from the use of latent variables in the modelling process. We conclude with an outlook on the future role of machine learning models in personality research and assessment.

Investigating the Relationships between Mobility Behaviours and Indicators of Subjective Well–Being Using Smartphone–Based Experience Sampling and GPS Tracking

People interact with their physical environments every day by visiting different places and moving between them. Such mobility behaviours likely influence and are influenced by people's subjective well–being. However, past research examining the links between mobility behaviours and well–being has been inconclusive. Here, we provide a comprehensive investigation of these relationships by examining individual differences in two types of mobility behaviours (movement patterns and places visited) and their relationship to six indicators of subjective well–being (depression, loneliness, anxiety, stress, affect, and energy) at two different temporal levels of analysis (two–week tendencies and daily level). Using data from a large smartphone–based longitudinal study ( N = 1765), we show that (i) movement patterns assessed via GPS data (distance travelled, entropy, and irregularity) and (ii) places visited assessed via experience sampling reports (home, work, and social places) are associated with subjective well–being at the between and within person levels. Our findings suggest that distance travelled is related to anxiety, affect, and stress, irregularity is related to depression and loneliness, and spending time in social places is negatively associated with loneliness. We discuss the implications of our work and highlight directions for future research on the generalizability to other populations as well as the characteristics of places. © 2020 European Association of Personality Psychology

Personality Sensing for Theory Development and Assessment in the Digital Age

People around the world own digital media devices that mediate and are in close proximity to their daily behaviours and situational contexts. These devices can be harnessed as sensing technologies to collect information from sensor and metadata logs that provide fine–grained records of everyday personality expression. In this paper, we present a conceptual framework and empirical illustration for personality sensing research, which leverages sensing technologies for personality theory development and assessment. To further empirical knowledge about the degree to which personality–relevant information is revealed via such data, we outline an agenda for three research domains that focus on the description, explanation, and prediction of personality. To illustrate the value of the personality sensing research agenda, we present findings from a large smartphone–based sensing study ( N = 633) characterizing individual differences in sensed behavioural patterns (physical activity, social behaviour, and smartphone use) and mapping sensed behaviours to the Big Five dimensions. For example, the findings show associations between behavioural tendencies and personality traits and daily behaviours and personality states. We conclude with a discussion of best practices and provide our outlook on how personality sensing will transform our understanding of personality and the way we conduct assessment in the years to come. © 2020 European Association of Personality Psychology

Personality-place transactions: Mapping the relationships between Big Five personality traits, states, and daily places

People actively select their environments, and the environments they select can alter their psychological characteristics in the moment and over time. Such dynamic person-environment transactions are likely to play out in the context of daily life via the places people spend time in (e.g., home, work, or public places like cafes and restaurants). This article investigates personality-place transactions at 3 conceptual levels: stable personality traits, momentary personality states, and short-term personality trait expressions. Three 2-week experience sampling studies (2 exploratory and 1 confirmatory with a total N = 2,350 and more than 63,000 momentary assessments) were used to provide the first large-scale evidence showing that people's stable Big Five traits are associated with the frequency with which they visit different places on a daily basis. For example, extraverted people reported spending less time at home and more time at cafés, bars, and friends' houses. The findings also show that spending time in a particular place predicts people's momentary personality states and their short-term trait expression over time. For example, people reported feeling more extraverted in the moment when spending time at bars/parties, cafés/restaurants, or friends' houses, compared with when at home. People who showed preferences for spending more time in these places also showed higher levels of short-term trait extraversion over the course of 2 weeks. The findings make theoretical contributions to environmental psychology, personality dynamics, as well as the person-environment transactions literature, and highlight practical implications for a world in which the places people visit can be easily captured via GPS sensors. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

A process-oriented approach to respecting privacy in the context of mobile phone tracking

Mobile phone tracking poses challenges to individual privacy because a phone's sensor data and metadata logs can reveal behavioral, contextual, and psychological information about the individual who uses the phone. Here, I argue for a process-oriented approach to respecting individual privacy in the context of mobile phone tracking by treating informed consent as a process, not a mouse click. This process-oriented approach allows individuals to exercise their privacy preferences and requires the design of self-tracking systems that facilitate transparency, opt-in default settings, and individual control over personal data, especially with regard to: (1) what kinds of personal data are being collected and (2) how the data are being used and shared. In sum, I argue for the development of self-tracking systems that put individual user privacy and control at their core, while enabling people to harness their personal data for self-insight and behavior change. This approach to mobile phone privacy is a radical departure from current standard data practices and has implications for a wide range of stakeholders, including individual users, researchers, and corporations.

Personality trait predictors and mental well-being correlates of exercise frequency across the academic semester

RATIONALE

Regular exercise is frequently recommended as a means of combating the negative effects of stress on mental health. But, among college students, exercise frequency remains below recommended levels.

OBJECTIVE

To better understand exercising behaviors in college students, we examined how exercise patterns change across an academic semester and how these changes relate to personality traits and mental well-being.

METHOD

We conducted two longitudinal experience sampling studies, using data from four cohorts of students, spanning four semesters (Fall 2015 - Spring 2017). In Study 1, a large sample of United States college students (cohort 1; N = 1126) reported the number of days they exercised and their levels of happiness, stress, sadness, and anxiety each week over the course of one academic semester (13 weeks). Study 2 (cohorts 2-4; N = 1973) was conducted to replicate our exploratory results from Study 1.

RESULTS

Using latent growth curve modeling, we observed the same normative pattern of change across both studies: The average student exercised twice during the first week of the semester and showed consistent decreases in exercise frequency in following weeks. Across both studies, higher initial levels of exercise frequency at the start of the semester were consistently related to higher extraversion, higher conscientiousness, and lower neuroticism. Furthermore, exercise frequency and mental well-being fluctuated together after controlling for time trends in the data: In weeks during which students exercised more than predicted, they also reported being happier and less anxious.

CONCLUSIONS

We contextualize the findings with regard to past research and discuss how they can be applied in behavior change interventions to promote students' well-being.

Sensing Behavioral Change over Time

Personality traits describe individual differences in patterns of thinking, feeling, and behaving ("between-person" variability). But individuals also show changes in their own patterns over time ("within-person" variability). Existing approaches to measuring within-person variability typically rely on self-report methods that do not account for fine-grained behavior change patterns (e.g., hour-by-hour). In this paper, we use passive sensing data from mobile phones to examine the extent to which within-person variability in behavioral patterns can predict self-reported personality traits. Data were collected from 646 college students who participated in a self-tracking assignment for 14 days. To measure variability in behavior, we focused on 5 sensed behaviors (ambient audio amplitude, exposure to human voice, physical activity, phone usage, and location data) and computed 4 within-person variability features (simple standard deviation, circadian rhythm, regularity index, and flexible regularity index). We identified a number of significant correlations between the within-person variability features and the self-reported personality traits. Finally, we designed a model to predict the personality traits from the within-person variability features. Our results show that we can predict personality traits with good accuracy. The resulting predictions correlate with self-reported personality traits in the range of r = 0.32, MAE = 0.45 (for Openness in iOS users) to r = 0.69, MAE = 0.55 (for Extraversion in Android users). Our results suggest that within-person variability features from smartphone data has potential for passive personality assessment.

Using Smartphones to Collect Behavioral Data in Psychological Science: Opportunities, Practical Considerations, and Challenges

Smartphones now offer the promise of collecting behavioral data unobtrusively, in situ, as it unfolds in the course of daily life. Data can be collected from the onboard sensors and other phone logs embedded in today's off-the-shelf smartphone devices. These data permit fine-grained, continuous collection of people's social interactions (e.g., speaking rates in conversation, size of social groups, calls, and text messages), daily activities (e.g., physical activity and sleep), and mobility patterns (e.g., frequency and duration of time spent at various locations). In this article, we have drawn on the lessons from the first wave of smartphone-sensing research to highlight areas of opportunity for psychological research, present practical considerations for designing smartphone studies, and discuss the ongoing methodological and ethical challenges associated with research in this domain. It is our hope that these practical guidelines will facilitate the use of smartphones as a behavioral observation tool in psychological science.

Capturing Situational Information with Smartphones and Mobile Sensing Methods

Smartphones are pervasive companions to many people as they go about their daily lives. In addition, they are equipped with a wide array of sensors making it possible to measure objective information about people and situations, many times, with great fidelity, over long periods of time, in a way that is both unobtrusive and ecologically valid. Therefore, we argue that smartphones and other forms of mobile sensing are ideally suited to measuring situations. In particular, we describe how sensing methods can be used to assess situational cues, characteristics and classes. Copyright © 2015 European Association of Personality Psychology

Personality Impressions of World of Warcraft Players Based on Their Avatars and Usernames

Every week an estimated 20 million people collectively spend hundreds of millions of hours playing massively multiplayer online role-playing games (MMORPGs). Here the authors investigate whether avatars in one such game, the World of Warcraft (WoW), convey accurate information about their players' personalities. They assessed consensus and accuracy of avatar-based impressions for 299 WoW players. The authors examined impressions based on avatars alone, and images of avatars presented along with usernames. The personality impressions yielded moderate consensus (avatar-only mean ICC = .32; avatar plus username mean ICC = .66), but no accuracy (avatar only mean r = .03; avatar plus username mean r = .01). A lens-model analysis suggests that observers made use of avatar features when forming impressions, but the features had little validity. Discussion focuses on what factors might explain the pattern of consensus but no accuracy, and on why the results might differ from those based on other virtual domains and virtual worlds.