Emily M. Hastings, Ph.D.

Emily M. Hastings, Ph.D.

Assistant Professor of Computer Science at the University of Wisconsin-Eau Claire (she/her)

Publications

You can also find my articles on my Google Scholar profile. See my Kudos page for non-technical descriptions of some of my papers.

Conferences and Journals

A Data-Driven Framework for Team Formation for Maintenance Tasks

Published in International Journal of Prognostics and Health Management, 2021

Even as maintenance evolves with new technologies, it is still a heavily human-driven domain; multiple steps in the maintenance workflow still require human expertise and intervention. Various maintenance activities require multiple maintainers, all with different skill sets and expertise, and from various positions and levels within the organization. Responding to maintenance requests, training exercises, or executing larger maintenance projects all can require maintenance teams. Having the correct assortment of individuals both in terms of skills and management experience can help improve the efficiency of these maintenance tasks. This paper presents a workflow for creating teams of maintainers by adapting accepted practices from the human-computer interaction (HCI) community. These steps provide a low-cost solution to help account for the needs of maintainers and their management, while matching skills of the maintainers with the needs of the activity.

Recommended citation: Reslan, M., Hastings, E., Brundage, M. P., & Sexton, T. (2021). A Data-Driven Framework for Team Formation for Maintenance Tasks. IJPHM, 12, 003.

Access online here. Download here.

LIFT: Integrating Stakeholder Voices into Algorithmic Team Formation

Published in Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, 2020

Team formation tools assume instructors should configure the criteria for creating teams, precluding students from participating in a process affecting their learning experience. We propose LIFT, a novel learner-centered workflow where students propose, vote for, and weigh the criteria used as inputs to the team formation algorithm. We conducted an experiment (N=289) comparing LIFT to the usual instructor-led process, and interviewed participants to evaluate their perceptions of LIFT and its outcomes. Learners proposed novel criteria not included in existing algorithmic tools, such as organizational style. They avoided criteria like gender and GPA that instructors frequently select, and preferred those promoting efficient collaboration. LIFT led to team outcomes comparable to those achieved by the instructor-led approach, and teams valued having control of the team formation process. We provide instructors and designers with a workflow and evidence supporting giving learners control of the algorithmic process used for grouping them into teams.

Recommended citation: Hastings, E. M., Alamri, A., Kuznetsov, A., Pisarczyk, C., Karahalios, K., Marinov, D., & Bailey, B. P. (2020, April). LIFT: Integrating Stakeholder Voices into Algorithmic Team Formation. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (pp. 1-13).

Access online here. Download here.

Agreement Behavior of Isolated Annotators for Maintenance Work-Order Data Mining

Published in Proceedings of the Annual Conference of the PHM Society 2019, 2019

Maintenance work orders (MWOs) are an integral part of the maintenance workflow. These documents allow technicians to capture vital aspects of a maintenance job, including observed symptoms, potential causes, and solutions implemented. MWOs have often been disregarded during analysis because of the unstructured nature of the text they contain. However, research efforts have recently emerged that clean MWOs for analysis. One such approach is a tagging method which relies on experts classifying and annotating the words used in the MWOs. This method greatly reduces the volume of words used in the MWOs and links words, including misspellings, that have the same or similar meanings. However, one issue with this approach and with the practical usage of data-annotation tools on the shop-floor more generally is the usage of only one expert annotator at a time. How do we know that the classifications of a single annotator are correct, or if it is, for example, feasible to divide the tagging task among multiple experts? This paper examines the agreement behavior of multiple isolated experts classifying and annotating MWO data, and provides implications for implementing this tagging technique in authentic contexts. The results described here will help improve MWO classification leading to more accurate analysis of MWOs for decision-making support.

Recommended citation: Hastings, E., Sexton, T., Brundage, M. P., & Hodkiewicz, M. (2019). Agreement Behavior of Isolated Annotators for Maintenance Work-Order Data Mining. Proceedings of the Annual Conference of the PHM Society, 11(1). https://doi.org/10.36001/phmconf.2019.v11i1.791

Access online here. Download here.

Structure or Nurture? The Effects of Team-Building Activities and Team Composition on Team Outcomes

Published in Proceedings of the ACM on Human-Computer Interaction - CSCW, 2018

How can instructors group students into teams that interact and learn effectively together? One strand of research advocates for grouping students into teams with "good" compositions such as skill diversity. Another strand argues for deploying team-building activities to foster interpersonal relations like psychological safety. Our work synthesizes these two strands of research. We describe an experiment (N=249) that compares how team composition vs. team-building activities affect student team outcomes. In two university courses, we composed student teams either randomly or using a criteria-based team formation tool. Teams further performed team-building activities that promoted either team or task outcomes. We collected project scores, and used surveys to measure psychological safety, perceived performance, and team satisfaction. Surprisingly, the criteria-based teams did not statistically differ from the random teams on any of the measures taken, despite having compositions that better satisfied the criteria defined by the instructor. Our findings argue that, for instructors deploying a team formation tool, creating an expectation among team members that their team can perform well is as important as tuning the criteria in the tool. We also found that student teams reported high levels of psychological safety, but these levels appeared to develop organically and were not affected by the activities or compositional strategies tested. We distill these and other findings into implications for the design and deployment of team formation tools for learning environments.

Recommended citation: Hastings, E. M., Jahanbakhsh, F., Karahalios, K., Marinov, D., & Bailey, B. P. (2018). Structure or Nurture?: The Effects of Team-Building Activities and Team Composition on Team Outcomes. Proceedings of the ACM on Human-Computer Interaction, 2(CSCW), 68.

Access online here. Download here.

Comparing Global Link Arrangements for Dragonfly Networks

Published in 2015 IEEE International Conference on Cluster Computing, 2015

High-performance computing systems are shifting away from traditional interconnect topologies to exploit new technologies and to reduce interconnect power consumption. The Dragonfly topology is one promising candidate for new systems, with several variations already in production. It is hierarchical, with local links forming groups and global links joining the groups. At each level, the interconnect is a clique, with a link between each pair of switches in a group and a link between each pair of groups. This paper shows that the intergroup links can be made in meaningfully different ways. We evaluate three previously-proposed approaches for link organization (called global link arrangements) in two ways. First, we use bisection bandwidth, an important and commonly-used measure of the potential for communication bottlenecks. We show that the global link arrangements often give bisection bandwidths differing by 10s of percent, with the specific separation varying based on the relative bandwidths of local and global links. For the link bandwidths used in a current Dragonfly implementation, it is 33%. Second, we show that the choice of global link arrangement can greatly impact the regularity of task mappings for nearest neighbor stencil communication patterns, an important pattern in scientific applications.

Recommended citation: Hastings, E., Rincon-Cruz, D., Spehlmann, M., Meyers, S., Xu, A., Bunde, D. P., & Leung, V. J. (2015, September). Comparing global link arrangements for dragonfly networks. In 2015 IEEE International Conference on Cluster Computing (pp. 361-370). IEEE.

Access online here.

Other Peer-Reviewed Publications

Introduction to Computer Science

Published in Common Ground Research Networks Learning Design and Leadership Modules, 2017

This learning module is intended to be an introduction to computer science suitable for K-12 students, along the same lines as the Girls Who Code program, or a summer College for Kids" course, though it would be equally applicable to beginning undergraduate students in their first computer science course. It provides an overview of what computer science is and what computer scientists do, an introduction to four key concepts of CS (loops, variables, conditionals, and functions), and suggestions for next steps students can take to continue their journey learning CS."

Recommended citation: Hastings, Emily. (2017, December 9). Introduction to Computer Science. Common Ground Research Networks Learning Design and Leadership Modules. Retrieved from https://cgscholar.com/bookstore/works/introduction-to-computer-science?category_id=364.

Access online here.

Learning Theory Exegesis: Collaborative Learning

Published in CGScholar EPSY 408 SU17 Community, 2017

Teamwork has become increasingly popular in recent years, with more and more workplaces expecting their employees to work collaboratively with each other. In response, organizations like the Accreditation Board for Engineering and Technology have increasingly required educational institutions to incorporate teamwork into their curricula, and a collaborative approach to learning has grown in popularity (Ruiz Ulloa & Adams, 2004). Like many students, I have always been a little wary of group work, having had bad experiences in the past. I have, however, had positive ones as well; there are a number of benefits to working collaboratively, including a shared (and so perhaps reduced) workload, exposure to different viewpoints, and the ability to take on larger projects. I am, therefore, interested in studying the theory behind collaborative learning, as I hope to one day help my own students experience the positive aspects of group learning while avoiding the negative ones. This topic is also closely related to my current projects for my Ph.D., a point to which I will return later.

Recommended citation: Hastings, Emily. (2017, July 17). Learning Theory Exegesis: Collaborative Learning. CGScholar EPSY 408 SU17 Community. Retrieved from https://cgscholar.com/community/profiles/user-28138/publications/143052.

Access online here.