Learning process modeling phases from modeling interactions and eye tracking data

Andrea Burattin*, Michael Kaiser, Manuel Neurauter, Barbara Weber

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

46 Downloads (Pure)

Abstract

The creation of a process model is a process consisting of five distinct phases, i.e., problem understanding, method finding, modeling, reconciliation, and validation. To enable a fine-grained analysis of process model creation based on phases or the development of phase-specific modeling support, an automatic approach to detect phases is needed. While approaches exist to automatically detect modeling and reconciliation phases based on user interactions, the detection of phases without user interactions (i.e., problem understanding, method finding, and validation) is still a problem. Exploiting a combination of user interactions and eye tracking data, this paper presents a two-step approach that is able to automatically detect the sequence of phases a modeler is engaged in during model creation. The evaluation of our approach shows promising results both in terms of quality as well as computation time demonstrating its feasibility.

Original languageEnglish
JournalData and Knowledge Engineering
Volume121
Pages (from-to)1-17
Number of pages17
ISSN0169-023X
DOIs
Publication statusPublished - 2019

Keywords

  • Automatic phase detection
  • Classification
  • Eye tracking
  • Interaction tracking
  • Process of process modeling
  • Sequence labeling

Cite this

@article{00b974b713b94080a98fb67a5c7faea2,
title = "Learning process modeling phases from modeling interactions and eye tracking data",
abstract = "The creation of a process model is a process consisting of five distinct phases, i.e., problem understanding, method finding, modeling, reconciliation, and validation. To enable a fine-grained analysis of process model creation based on phases or the development of phase-specific modeling support, an automatic approach to detect phases is needed. While approaches exist to automatically detect modeling and reconciliation phases based on user interactions, the detection of phases without user interactions (i.e., problem understanding, method finding, and validation) is still a problem. Exploiting a combination of user interactions and eye tracking data, this paper presents a two-step approach that is able to automatically detect the sequence of phases a modeler is engaged in during model creation. The evaluation of our approach shows promising results both in terms of quality as well as computation time demonstrating its feasibility.",
keywords = "Automatic phase detection, Classification, Eye tracking, Interaction tracking, Process of process modeling, Sequence labeling",
author = "Andrea Burattin and Michael Kaiser and Manuel Neurauter and Barbara Weber",
year = "2019",
doi = "10.1016/j.datak.2019.04.001",
language = "English",
volume = "121",
pages = "1--17",
journal = "Data & Knowledge Engineering",
issn = "0169-023X",
publisher = "Elsevier",

}

Learning process modeling phases from modeling interactions and eye tracking data. / Burattin, Andrea; Kaiser, Michael; Neurauter, Manuel; Weber, Barbara.

In: Data and Knowledge Engineering, Vol. 121, 2019, p. 1-17.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Learning process modeling phases from modeling interactions and eye tracking data

AU - Burattin, Andrea

AU - Kaiser, Michael

AU - Neurauter, Manuel

AU - Weber, Barbara

PY - 2019

Y1 - 2019

N2 - The creation of a process model is a process consisting of five distinct phases, i.e., problem understanding, method finding, modeling, reconciliation, and validation. To enable a fine-grained analysis of process model creation based on phases or the development of phase-specific modeling support, an automatic approach to detect phases is needed. While approaches exist to automatically detect modeling and reconciliation phases based on user interactions, the detection of phases without user interactions (i.e., problem understanding, method finding, and validation) is still a problem. Exploiting a combination of user interactions and eye tracking data, this paper presents a two-step approach that is able to automatically detect the sequence of phases a modeler is engaged in during model creation. The evaluation of our approach shows promising results both in terms of quality as well as computation time demonstrating its feasibility.

AB - The creation of a process model is a process consisting of five distinct phases, i.e., problem understanding, method finding, modeling, reconciliation, and validation. To enable a fine-grained analysis of process model creation based on phases or the development of phase-specific modeling support, an automatic approach to detect phases is needed. While approaches exist to automatically detect modeling and reconciliation phases based on user interactions, the detection of phases without user interactions (i.e., problem understanding, method finding, and validation) is still a problem. Exploiting a combination of user interactions and eye tracking data, this paper presents a two-step approach that is able to automatically detect the sequence of phases a modeler is engaged in during model creation. The evaluation of our approach shows promising results both in terms of quality as well as computation time demonstrating its feasibility.

KW - Automatic phase detection

KW - Classification

KW - Eye tracking

KW - Interaction tracking

KW - Process of process modeling

KW - Sequence labeling

U2 - 10.1016/j.datak.2019.04.001

DO - 10.1016/j.datak.2019.04.001

M3 - Journal article

VL - 121

SP - 1

EP - 17

JO - Data & Knowledge Engineering

JF - Data & Knowledge Engineering

SN - 0169-023X

ER -