Activity matching with human intelligence

Carlos RodríGuez, Christopher Klinkmüller, Ingo Weber, Florian Daniel, Fabio Casati

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Effective matching of activities is the first step toward successful process model matching and search. The problem is nontrivial and has led to a variety of computational similarity metrics and matching approaches, however all still with low performance in terms of precision and recall. In this paper, instead, we study how to leverage on human intelligence to identify matches among activities and show that the problem is not as straightforward as most computational approaches assume. We access human intelligence (i) by crowdsourcing the activity matching problem to generic workers and (ii) by eliciting ground truth matches from experts. The precision and recall we achieve and the qualitative analysis of the results testify huge potential for a human-based activity matching that contemplates disagreement and interpretation.

Original languageEnglish
Title of host publicationBusiness Process Management Forum - BPM Forum, 2016, Proceedings
PublisherSpringer Verlag
Pages124-140
Number of pages17
Volume260
ISBN (Print)9783319454672
DOIs
Publication statusPublished - 2016
Externally publishedYes
EventInternational Conference on Business Process Management, BPM 2016 - Rio de Janeiro, Brazil
Duration: 18 Sep 201622 Sep 2016

Publication series

NameLecture Notes in Business Information Processing
Volume260
ISSN (Print)1865-1348

Conference

ConferenceInternational Conference on Business Process Management, BPM 2016
CountryBrazil
CityRio de Janeiro
Period18.9.1622.9.16

Fingerprint

Model Matching
Matching Problem
Qualitative Analysis
Leverage
Process Model
Metric
Intelligence
Human
Interpretation
Similarity
Truth
Matching problem
Process model
Workers
Qualitative analysis
Search and matching

Keywords

  • Activity matching
  • Crowdsourcing
  • Label matching

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Management Information Systems
  • Business and International Management
  • Information Systems
  • Modelling and Simulation
  • Information Systems and Management

Cite this

RodríGuez, C., Klinkmüller, C., Weber, I., Daniel, F., & Casati, F. (2016). Activity matching with human intelligence. In Business Process Management Forum - BPM Forum, 2016, Proceedings (Vol. 260, pp. 124-140). (Lecture Notes in Business Information Processing; Vol. 260). Springer Verlag. https://doi.org/10.1007/978-3-319-45468-9_8

Activity matching with human intelligence. / RodríGuez, Carlos; Klinkmüller, Christopher; Weber, Ingo; Daniel, Florian; Casati, Fabio.

Business Process Management Forum - BPM Forum, 2016, Proceedings. Vol. 260 Springer Verlag, 2016. p. 124-140 (Lecture Notes in Business Information Processing; Vol. 260).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

RodríGuez, C, Klinkmüller, C, Weber, I, Daniel, F & Casati, F 2016, Activity matching with human intelligence. in Business Process Management Forum - BPM Forum, 2016, Proceedings. vol. 260, Lecture Notes in Business Information Processing, vol. 260, Springer Verlag, pp. 124-140, International Conference on Business Process Management, BPM 2016, Rio de Janeiro, Brazil, 18.9.16. https://doi.org/10.1007/978-3-319-45468-9_8
RodríGuez C, Klinkmüller C, Weber I, Daniel F, Casati F. Activity matching with human intelligence. In Business Process Management Forum - BPM Forum, 2016, Proceedings. Vol. 260. Springer Verlag. 2016. p. 124-140. (Lecture Notes in Business Information Processing). https://doi.org/10.1007/978-3-319-45468-9_8
RodríGuez, Carlos ; Klinkmüller, Christopher ; Weber, Ingo ; Daniel, Florian ; Casati, Fabio. / Activity matching with human intelligence. Business Process Management Forum - BPM Forum, 2016, Proceedings. Vol. 260 Springer Verlag, 2016. pp. 124-140 (Lecture Notes in Business Information Processing).
@inproceedings{4c8f364db771475a8d37a746c58ae0c1,
title = "Activity matching with human intelligence",
abstract = "Effective matching of activities is the first step toward successful process model matching and search. The problem is nontrivial and has led to a variety of computational similarity metrics and matching approaches, however all still with low performance in terms of precision and recall. In this paper, instead, we study how to leverage on human intelligence to identify matches among activities and show that the problem is not as straightforward as most computational approaches assume. We access human intelligence (i) by crowdsourcing the activity matching problem to generic workers and (ii) by eliciting ground truth matches from experts. The precision and recall we achieve and the qualitative analysis of the results testify huge potential for a human-based activity matching that contemplates disagreement and interpretation.",
keywords = "Activity matching, Crowdsourcing, Label matching",
author = "Carlos Rodr{\'i}Guez and Christopher Klinkm{\"u}ller and Ingo Weber and Florian Daniel and Fabio Casati",
year = "2016",
doi = "10.1007/978-3-319-45468-9_8",
language = "English",
isbn = "9783319454672",
volume = "260",
series = "Lecture Notes in Business Information Processing",
publisher = "Springer Verlag",
pages = "124--140",
booktitle = "Business Process Management Forum - BPM Forum, 2016, Proceedings",
address = "Germany",

}

TY - GEN

T1 - Activity matching with human intelligence

AU - RodríGuez, Carlos

AU - Klinkmüller, Christopher

AU - Weber, Ingo

AU - Daniel, Florian

AU - Casati, Fabio

PY - 2016

Y1 - 2016

N2 - Effective matching of activities is the first step toward successful process model matching and search. The problem is nontrivial and has led to a variety of computational similarity metrics and matching approaches, however all still with low performance in terms of precision and recall. In this paper, instead, we study how to leverage on human intelligence to identify matches among activities and show that the problem is not as straightforward as most computational approaches assume. We access human intelligence (i) by crowdsourcing the activity matching problem to generic workers and (ii) by eliciting ground truth matches from experts. The precision and recall we achieve and the qualitative analysis of the results testify huge potential for a human-based activity matching that contemplates disagreement and interpretation.

AB - Effective matching of activities is the first step toward successful process model matching and search. The problem is nontrivial and has led to a variety of computational similarity metrics and matching approaches, however all still with low performance in terms of precision and recall. In this paper, instead, we study how to leverage on human intelligence to identify matches among activities and show that the problem is not as straightforward as most computational approaches assume. We access human intelligence (i) by crowdsourcing the activity matching problem to generic workers and (ii) by eliciting ground truth matches from experts. The precision and recall we achieve and the qualitative analysis of the results testify huge potential for a human-based activity matching that contemplates disagreement and interpretation.

KW - Activity matching

KW - Crowdsourcing

KW - Label matching

UR - http://www.scopus.com/inward/record.url?scp=84988585386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988585386&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-45468-9_8

DO - 10.1007/978-3-319-45468-9_8

M3 - Conference contribution

AN - SCOPUS:84988585386

SN - 9783319454672

VL - 260

T3 - Lecture Notes in Business Information Processing

SP - 124

EP - 140

BT - Business Process Management Forum - BPM Forum, 2016, Proceedings

PB - Springer Verlag

ER -