A Multisensor Person-Centered Approach to Understand the Role of Daily Activities in Job Performance with Organizational Personas

Abstract

Several psychologists posit that performance is not only a function of personality but also of situational contexts, such as day-level activities. Yet in practice, since only personality assessments are used to infer job performance, they provide a limited perspective by ignoring activity. However, multi-modal sensing has the potential to characterize these daily activities. This paper illustrates how empirically measured activity data complements traditional effects of personality to explain a worker's performance. We leverage sensors in commodity devices to quantify the activity context of 603 information workers. By applying classical clustering methods on this multisensor data, we take a person-centered approach to describe workers in terms of both personality and activity. We encapsulate both these facets into an analytical framework that we call organizational personas. On interpreting these organizational personas we find empirical evidence to support that, independent of a worker's personality, their activity is associated with job performance. While the effects of personality are consistent with the literature, we find that the activity is equally effective in explaining organizational citizenship behavior and is less but significantly effective for task proficiency and deviant behaviors. Specifically, personas that exhibit a daily-activity pattern with fewer location visits, batched phone-use, shorter desk-sessions and longer sleep duration, tend to perform better on all three performance metrics. Organizational personas are a descriptive framework to identify the testable hypotheses that can disentangle the role of malleable aspects like activity in determining the performance of a worker population.

Social Media and Ubiquitous Technologies for Remote Worker Wellbeing and Productivity in a Post-Pandemic World

“…After all, it is much more convenient to deploy a one-time personality assessment. However, Das Swain et al have shown that a worker's day-level activities explain their performance above and beyond their personality [18]. In this work, the authors used activity logs from smartphones, wearables and bluetooth beacons to distinguish its effects from the workers' personality.…”

“…Particularly, in their dataset, workers who batch their phone use, spend shorter sessions at their desk, and sleep more performed better irrespective of their personality being "resilient" or "undercontrolled" (Figure 1). Not only does an understanding of day-level activity make studies of performance more comprehensive, for certain metrics such as Organizational Citizenship Behavior -often referred to as Contextual Performance -day-level activities explain approximately 50% variance [18].…”

“…The backdrop of a pandemic and remote work may also increase the challenges of conducting such evaluations that require face-to-face physical interactions [10]. This has been the key motivation to explore pervasive technologies to understand worker outcomes in unobtrusive and automatic ways [11,12,13,14,15,16,17,18]. This new future of work thus draws on many years of effort in the computer supported cooperative work (CSCW) and human-computer interaction (HCI) community towards augmenting worker collaboration, coordination, and engagement [19,20,21,22].…”

Understanding User Behavior in Car Sharing Services Through The Lens of Mobility

“…Our study has several limitations about the generalizability of findings, which are similar to many other IMWUT works [13,17,27,29,39] due to the specific region or product investigation. First of all, we only investigated car sharing user behavior in China.…”

Causal Factors of Effective Psychosocial Outcomes in Online Mental Health Communities

“…We control our models with the same covariates used in matching. We eliminate correlated features using variance inflation factor (threshold = 10) (Das Swain et al 2019, Miles 2014). We also include regularizations (L1, L2) and interaction terms (degree 2) in the regression models.…”