Adaptive Assistance Systems for Academic Procrastination

Designing Information Systems for Personal Productivity

A multi-method research project for understanding, measuring, and mitigating habitual social media use during intended study periods through personalized, theory-grounded digital interventions.

The project aims to establish an empirically grounded understanding of social media-driven academic procrastination and to design context-sensitive micro-interventions that address individual differences in triggers, mechanisms, and self-regulation resources.

Overview

Motivation

Academic procrastination is a persistent and consequential problem in higher education. In university contexts - characterized by substantial autonomy and limited external structure - students must rely heavily on self-regulation. At the same time, algorithmically curated platforms provide powerful, immediately rewarding alternatives to academic engagement, turning procrastination into a rapid, habitual shift into social media consumption that is difficult to interrupt once initiated.

  • Existing intervention approaches exhibit several key limitations:
  • Generic features (e.g. blockers, reminders) that treat students as largely homogeneous.
  • Focus on surface-level behavior change rather than the underlying motivational, affective, and habitual mechanisms driving delay.
  • Reliance on retrospective self-reports, making it difficult to capture episodes in situ.
  • Limited personalization and poor alignment with the momentary conditions under which procrastination unfolds.

These deficits make it particularly difficult to design support that is both scalable and effective for individual students in real study contexts.

Expected Contribution

The project aims to bridge the gap between generic productivity tools and theoretically grounded, personalized intervention design. By the end of the project, we will mainly provide:

  • A Context-Sensitive Measurement Approach: Operationalization methods that go beyond retrospective self-report by combining validated scales with behavioral and contextual indicators such as app-opening events and screen time data.
  • A Personalized Digital Micro-Intervention: A theory-grounded Behavior Change Support System with a Just-in-Time Adaptive Intervention (JITAI) architecture, designed for one high-relevance student archetype and evaluated in realistic study contexts.
  • Transferable Design Knowledge: A reusable blueprint for IS researchers and designers developing comparable personalized micro-interventions in other domains, such as workplace stress management or loneliness.

Research Approach

The project follows an echeloned Design Science Research (eDSR) methodology, organizing the work into self-contained, iteratively validated phases that link problem understanding and artifact design. The methodological approach includes for instance:

  • Synthesis of procrastination drivers, usage patterns, and existing digital interventions.
  • Interviews reconstructing recent procrastination episodes to capture triggers, responses, and consequences.
  • Collaborative design and formative testing of a prototype intervention with student participants.
  • A randomized field experiment evaluating feasibility, acceptability, and effectiveness in realistic study contexts.

This approach bridges rigorous behavioral science with practical, user-centered artifact development.

Project Features

Person-Sensitive Design:

Interventions matched to individual predisposition and mechanism profiles rather than applied uniformly.

Episode-Level Measurement:

Behavioral and contextual indicators that capture procrastination in that capture procrastination in the moment rather than in retrospect

Productivity & Well-Being Integration:

Simultaneous consideration of efficiency, cognitive sustainability, and individual well-being.

Experimental Validation:

Empirical evaluation of interventions through experiments, field studies, and surveys.

Duration

2022 – ongoing

1.    Aral, S., Brynjolfsson, E., & Van Alstyne, M. (2012). Information, technology, and information worker productivity. Information Systems Research, 23(3-part-2), 849-867.
2.    Jones, E. C., & Chung, C. A. (2006). A methodology for measuring engineering knowledge worker productivity. Engineering Management Journal, 18(1), 32-38.
3.    Sumanth, D. J., Omachonu, V. K., & Beruvides, M. G. (1990). A review of the state–of–the–art research on white–collar/knowledge–worker productivity. International Journal of Technology Management, 5(3), 337-355.
4.    Palvalin, M., Lönnqvist, A., & Vuolle, M. (2013). Analysing the impacts of ICT on knowledge work productivity. Journal of Knowledge Management.
5.    Noruzy, A., Hayat, A. A., Rezazadeh, A., Najafi, S., & Hatami-Shirkouhi, L. (2011). Factors influencing the productivity of knowledge workers: a case study from an Iranian Oil Company. International Journal of Productivity and Quality Management, 8(4), 459-479.
6.    Butt, M. A., Nawaz, F., Hussain, S., Sousa, M. J., Wang, M., Sumbal, M. S., & Shujahat, M. (2019). Individual knowledge management engagement, knowledge-worker productivity, and innovation performance in knowledge-based organizations: the implications for knowledge processes and knowledge-based systems. Computational and Mathematical Organization Theory, 25, 336-356.
7.    Adriaenssen, D. J., Johannessen, D. A., & Johannessen, J. A. (2016). Knowledge management and performance: developing a theoretical approach to knowledge workers’ productivity, and practical tools for managers. Problems and Perspectives in Management, 14(3), 667-676.
8.    Yusoff, M. Z., Mahmuddin, M., & Ahmad, M. (2017). The effect of knowledge work productivity factors on software development. Journal of Engineering Science and Technology Special, 12(Special Issue), 64-73.
9.    Kianto, A., Shujahat, M., Hussain, S., Nawaz, F., & Ali, M. (2019). The impact of knowledge management on knowledge worker productivity. Baltic Journal of Management, 14(2), 178-197.
10.    Palvalin, M. (2019). What matters for knowledge work productivity?. Employee Relations, 41(1), 209-227.
11.    Karr-Wisniewski, P., & Lu, Y. (2010). When more is too much: Operationalizing technology overload and exploring its impact on knowledge worker productivity. Computers in Human Behavior, 26(5), 1061-1072.
12.    Leshed, G. (2012). Slowing down with personal productivity tools. Interactions, 19(1), 58-63.
13.    Óskarsdóttir, H. G., Oddsson, G. V., Sturluson, J. Þ., & Sæmundsson, R. J. (2022). Towards a holistic framework of knowledge worker productivity. Administrative Sciences, 12(2), 50.
14.    Soto, M., Satterfield, C., Fritz, T., Murphy, G. C., Shepherd, D. C., & Kraft, N. (2021). Observing and predicting knowledge worker stress, focus and awakeness in the wild. International Journal of Human-Computer Studies, 146, 102560.

Team