Who is behind the Model? Classifying Modelers based on Pragmatic Model Features

Andrea Burattin; Pnina Soffer; Dirk Fahland; Jan Mendling; Hajo A. Reijers; Irene Vanderfeesten; Matthias Weidlich; Barbara Weber

doi:10.1007/978-3-319-98648-7_19

Who is behind the Model? Classifying Modelers based on Pragmatic Model Features

Andrea Burattin, Pnina Soffer, Dirk Fahland, Jan Mendling, Hajo A. Reijers, Irene Vanderfeesten, Matthias Weidlich, Barbara Weber

Department of Applied Mathematics and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

348 Downloads (Pure)

Abstract

Process modeling tools typically aid end users in generic, non-personalized ways. However, it is well conceivable that different types of end users may profit from different types of modeling support. In this paper, we propose an approach based on machine learning that is able to classify modelers regarding their expertise while they are creating a process model. To do so, it takes into account pragmatic features of the model under development. The proposed approach is fully automatic, unobtrusive, tool independent, and based on objective measures. An evaluation based on two data sets resulted in a prediction performance of around 90%. Our results further show that all features can be efficiently calculated, which makes the approach applicable to online settings like adaptive modeling environments. In this way, this work contributes to improving the performance of process modelers.

Original language	English
Title of host publication	Business Process Management
Publisher	Springer
Publication date	2018
Pages	322-338
ISBN (Print)	978-3-319-98647-0
DOIs	https://doi.org/10.1007/978-3-319-98648-7_19
Publication status	Published - 2018
Event	16th International Conference on Business Process Management - University of Technology in Sydney, Sydney, Australia Duration: 9 Sept 2018 → 14 Sept 2018 Conference number: 16 http://bpm2018.web.cse.unsw.edu.au/

Conference

Conference	16th International Conference on Business Process Management
Number	16
Location	University of Technology in Sydney
Country/Territory	Australia
City	Sydney
Period	09/09/2018 → 14/09/2018
Internet address	http://bpm2018.web.cse.unsw.edu.au/

Series	Lecture Notes in Computer Science
Volume	11080
ISSN	0302-9743

Keywords

Process Modeling
Classification of modelers
Model layout

Access to Document

10.1007/978-3-319-98648-7_19

Paper 2 Accepted author manuscript, 1.47 MB

OpenUrl availability

Full text

Cite this

@inproceedings{e4b850351de64f76817260a2db11fd3a,

title = "Who is behind the Model? Classifying Modelers based on Pragmatic Model Features",

abstract = "Process modeling tools typically aid end users in generic, non-personalized ways. However, it is well conceivable that different types of end users may profit from different types of modeling support. In this paper, we propose an approach based on machine learning that is able to classify modelers regarding their expertise while they are creating a process model. To do so, it takes into account pragmatic features of the model under development. The proposed approach is fully automatic, unobtrusive, tool independent, and based on objective measures. An evaluation based on two data sets resulted in a prediction performance of around 90%. Our results further show that all features can be efficiently calculated, which makes the approach applicable to online settings like adaptive modeling environments. In this way, this work contributes to improving the performance of process modelers.",

keywords = "Process Modeling, Classification of modelers, Model layout",

author = "Andrea Burattin and Pnina Soffer and Dirk Fahland and Jan Mendling and Reijers, {Hajo A.} and Irene Vanderfeesten and Matthias Weidlich and Barbara Weber",

year = "2018",

doi = "10.1007/978-3-319-98648-7_19",

language = "English",

isbn = "978-3-319-98647-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "322--338",

booktitle = "Business Process Management",

note = "16th International Conference on Business Process Management , BPM 2018 ; Conference date: 09-09-2018 Through 14-09-2018",

url = "http://bpm2018.web.cse.unsw.edu.au/",

}

Burattin, A, Soffer, P, Fahland, D, Mendling, J, Reijers, HA, Vanderfeesten, I, Weidlich, M & Weber, B 2018, Who is behind the Model? Classifying Modelers based on Pragmatic Model Features. in Business Process Management . Springer, Lecture Notes in Computer Science, vol. 11080, pp. 322-338, 16th International Conference on Business Process Management , Sydney, New South Wales, Australia, 09/09/2018. https://doi.org/10.1007/978-3-319-98648-7_19

TY - GEN

T1 - Who is behind the Model? Classifying Modelers based on Pragmatic Model Features

AU - Burattin, Andrea

AU - Soffer, Pnina

AU - Fahland, Dirk

AU - Mendling, Jan

AU - Reijers, Hajo A.

AU - Vanderfeesten, Irene

AU - Weidlich, Matthias

AU - Weber, Barbara

N1 - Conference code: 16

PY - 2018

Y1 - 2018

N2 - Process modeling tools typically aid end users in generic, non-personalized ways. However, it is well conceivable that different types of end users may profit from different types of modeling support. In this paper, we propose an approach based on machine learning that is able to classify modelers regarding their expertise while they are creating a process model. To do so, it takes into account pragmatic features of the model under development. The proposed approach is fully automatic, unobtrusive, tool independent, and based on objective measures. An evaluation based on two data sets resulted in a prediction performance of around 90%. Our results further show that all features can be efficiently calculated, which makes the approach applicable to online settings like adaptive modeling environments. In this way, this work contributes to improving the performance of process modelers.

AB - Process modeling tools typically aid end users in generic, non-personalized ways. However, it is well conceivable that different types of end users may profit from different types of modeling support. In this paper, we propose an approach based on machine learning that is able to classify modelers regarding their expertise while they are creating a process model. To do so, it takes into account pragmatic features of the model under development. The proposed approach is fully automatic, unobtrusive, tool independent, and based on objective measures. An evaluation based on two data sets resulted in a prediction performance of around 90%. Our results further show that all features can be efficiently calculated, which makes the approach applicable to online settings like adaptive modeling environments. In this way, this work contributes to improving the performance of process modelers.

KW - Process Modeling

KW - Classification of modelers

KW - Model layout

U2 - 10.1007/978-3-319-98648-7_19

DO - 10.1007/978-3-319-98648-7_19

M3 - Article in proceedings

SN - 978-3-319-98647-0

T3 - Lecture Notes in Computer Science

SP - 322

EP - 338

BT - Business Process Management

PB - Springer

T2 - 16th International Conference on Business Process Management

Y2 - 9 September 2018 through 14 September 2018

ER -

Who is behind the Model? Classifying Modelers based on Pragmatic Model Features

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this