Evaluating a Knowledge-Based Scheduling Assistant (Article Abstract)

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

10 Downloads (Pure)

Abstract

We summarize a recent article that studies the evaluation of a knowledge-based scheduling system. The article considers a user-adaptive personal assistant agent designed to assist a busy knowledge worker in time management. We examine the managerial and technical challenges of designing adequate evaluation and the tension of collecting adequate data without a fully functional, deployed system. The PTIME agent was part of the CALO project, a seminal multi-institution effort to develop a personalized cognitive assistant. The project included a significant attempt to rigorously quantify learning capability in the context of automated scheduling assistance. Retrospection on negative and positive experiences over the six years of the project underscores best practice in evaluating user-adaptive systems. Through the lessons illustrated from the case study, the article highlights how development and infusion of innovative technology must be supported by adequate evaluation of its efficacy.
Original languageEnglish
Title of host publicationProceedings of the ICAPS'18 Workshop on Knowledge Engineering for Planning and Scheduling (KEPS'18)
Place of PublicationDelft, Netherlands
Pages1-2
Publication statusPublished - Jun 2018
Event28th International Conference on Automated Planning and Scheduling: KEPS 2018 - Delft, Delft, Netherlands
Duration: 24 Jun 201829 Jun 2018
Conference number: 28
http://www.icaps-conference.org

Conference

Conference28th International Conference on Automated Planning and Scheduling
Abbreviated titleICAPS 2018
CountryNetherlands
CityDelft
Period24/06/1829/06/18
Internet address

Fingerprint

Dive into the research topics of 'Evaluating a Knowledge-Based Scheduling Assistant (Article Abstract)'. Together they form a unique fingerprint.

Cite this