Predictive value of comments in the service engagement process

Stephen Carman, Ray Strong, Anca Chandra, Sechan Oh, Scott Spangler, Laura Anderson, Bernard Jansen

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

From the point of view of service providers, a service engagement process begins at the time an opportunity is known and concludes when a proposal for service delivery is resolved (won, lost or canceled). As such, understanding the service engagement process is critical for many businesses. This paper reports an application of text analytics to predict the engagement outcomes of service engagement opportunities based on written text comments about the opportunities during the course of the engagement processes. The comments are attached to documents, which also contain formally prepared solution proposals for potential deals. We examine whether the comments provide value by predicting the outcome of the engagement. Our final data set was 1,000 engagements and approximately 20,000 comments. We designed and carried out two experiments: one building a general classifier that would predict outcomes from comments; and the other building a one-sided classifier that could provide an advance warning for a significant subset of the deals with one particular outcome. The classifier achieved a 96% precision (4 percent false positives) for the cancel class and also a 96% recall on the full set of training documents. Our experiments show the predictive value of comments or service providers during service engagement and provide an interesting indication of trend in the practice of providing comments.

Original languageEnglish
JournalProceedings of the ASIST Annual Meeting
Volume49
Issue number1
DOIs
Publication statusPublished - 2012
Externally publishedYes

Fingerprint

Classifiers
service provider
Experiments
experiment
indication
Industry
trend
Values

Keywords

  • Crowdsourcing
  • Data mining
  • Services science
  • Text analytics

ASJC Scopus subject areas

  • Information Systems
  • Library and Information Sciences

Cite this

Predictive value of comments in the service engagement process. / Carman, Stephen; Strong, Ray; Chandra, Anca; Oh, Sechan; Spangler, Scott; Anderson, Laura; Jansen, Bernard.

In: Proceedings of the ASIST Annual Meeting, Vol. 49, No. 1, 2012.

Research output: Contribution to journalArticle

Carman, Stephen ; Strong, Ray ; Chandra, Anca ; Oh, Sechan ; Spangler, Scott ; Anderson, Laura ; Jansen, Bernard. / Predictive value of comments in the service engagement process. In: Proceedings of the ASIST Annual Meeting. 2012 ; Vol. 49, No. 1.
@article{c2a4d1ae11fb4d308d8e497b17fe4b9a,
title = "Predictive value of comments in the service engagement process",
abstract = "From the point of view of service providers, a service engagement process begins at the time an opportunity is known and concludes when a proposal for service delivery is resolved (won, lost or canceled). As such, understanding the service engagement process is critical for many businesses. This paper reports an application of text analytics to predict the engagement outcomes of service engagement opportunities based on written text comments about the opportunities during the course of the engagement processes. The comments are attached to documents, which also contain formally prepared solution proposals for potential deals. We examine whether the comments provide value by predicting the outcome of the engagement. Our final data set was 1,000 engagements and approximately 20,000 comments. We designed and carried out two experiments: one building a general classifier that would predict outcomes from comments; and the other building a one-sided classifier that could provide an advance warning for a significant subset of the deals with one particular outcome. The classifier achieved a 96{\%} precision (4 percent false positives) for the cancel class and also a 96{\%} recall on the full set of training documents. Our experiments show the predictive value of comments or service providers during service engagement and provide an interesting indication of trend in the practice of providing comments.",
keywords = "Crowdsourcing, Data mining, Services science, Text analytics",
author = "Stephen Carman and Ray Strong and Anca Chandra and Sechan Oh and Scott Spangler and Laura Anderson and Bernard Jansen",
year = "2012",
doi = "10.1002/meet.14504901215",
language = "English",
volume = "49",
journal = "Proceedings of the ASIST Annual Meeting",
issn = "1550-8390",
publisher = "Learned Information",
number = "1",

}

TY - JOUR

T1 - Predictive value of comments in the service engagement process

AU - Carman, Stephen

AU - Strong, Ray

AU - Chandra, Anca

AU - Oh, Sechan

AU - Spangler, Scott

AU - Anderson, Laura

AU - Jansen, Bernard

PY - 2012

Y1 - 2012

N2 - From the point of view of service providers, a service engagement process begins at the time an opportunity is known and concludes when a proposal for service delivery is resolved (won, lost or canceled). As such, understanding the service engagement process is critical for many businesses. This paper reports an application of text analytics to predict the engagement outcomes of service engagement opportunities based on written text comments about the opportunities during the course of the engagement processes. The comments are attached to documents, which also contain formally prepared solution proposals for potential deals. We examine whether the comments provide value by predicting the outcome of the engagement. Our final data set was 1,000 engagements and approximately 20,000 comments. We designed and carried out two experiments: one building a general classifier that would predict outcomes from comments; and the other building a one-sided classifier that could provide an advance warning for a significant subset of the deals with one particular outcome. The classifier achieved a 96% precision (4 percent false positives) for the cancel class and also a 96% recall on the full set of training documents. Our experiments show the predictive value of comments or service providers during service engagement and provide an interesting indication of trend in the practice of providing comments.

AB - From the point of view of service providers, a service engagement process begins at the time an opportunity is known and concludes when a proposal for service delivery is resolved (won, lost or canceled). As such, understanding the service engagement process is critical for many businesses. This paper reports an application of text analytics to predict the engagement outcomes of service engagement opportunities based on written text comments about the opportunities during the course of the engagement processes. The comments are attached to documents, which also contain formally prepared solution proposals for potential deals. We examine whether the comments provide value by predicting the outcome of the engagement. Our final data set was 1,000 engagements and approximately 20,000 comments. We designed and carried out two experiments: one building a general classifier that would predict outcomes from comments; and the other building a one-sided classifier that could provide an advance warning for a significant subset of the deals with one particular outcome. The classifier achieved a 96% precision (4 percent false positives) for the cancel class and also a 96% recall on the full set of training documents. Our experiments show the predictive value of comments or service providers during service engagement and provide an interesting indication of trend in the practice of providing comments.

KW - Crowdsourcing

KW - Data mining

KW - Services science

KW - Text analytics

UR - http://www.scopus.com/inward/record.url?scp=84878587737&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878587737&partnerID=8YFLogxK

U2 - 10.1002/meet.14504901215

DO - 10.1002/meet.14504901215

M3 - Article

AN - SCOPUS:84878587737

VL - 49

JO - Proceedings of the ASIST Annual Meeting

JF - Proceedings of the ASIST Annual Meeting

SN - 1550-8390

IS - 1

ER -