Integrated Machine-Learning Algorithm for Identifying Segment-Level Key Drivers from Consumers’ Online Review Data

Research output: Contribution to conferencePaper

Abstract

I propose a newly integrated machine-learning methodology to apply a classic model-based segmentation method to unstructured online review data. The proposed algorithm extracts an independent variables matrix from unstructured textual reviews by developing a set of text-mining algorithms and then identifies segment-level key drivers by applying a proposed Bayesian ordinal probit mixture regression with variable selection. With the proposed method, firms can focus on key drivers per each segment in their marketing activities (e.g., online banner advertising, search advertising); this method will help them systematically keep track of periodic patterns of segment-level key drivers. Using online data from a large review site for rating professors, I validate the extracted independent variables through multiple validation studies and then show heterogeneous key drivers for satisfaction across three derived segments. For the least satisfied segment, the proportion of reviewers is significantly higher from the Science, Technology, Engineering, and Mathematics education category.

Original languageEnglish (US)
StatePublished - Jan 1 2018
Event38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017 - Seoul, Korea, Republic of
Duration: Dec 10 2017Dec 13 2017

Other

Other38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017
CountryKorea, Republic of
CitySeoul
Period12/10/1712/13/17

Fingerprint

Learning algorithms
Learning systems
Marketing
Education
STEM (science, technology, engineering and mathematics)

Keywords

  • Machine learning
  • Market segmentation
  • Online textual reviews
  • Text mining
  • Variable selection

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Kim, S. (2018). Integrated Machine-Learning Algorithm for Identifying Segment-Level Key Drivers from Consumers’ Online Review Data. Paper presented at 38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017, Seoul, Korea, Republic of.

Integrated Machine-Learning Algorithm for Identifying Segment-Level Key Drivers from Consumers’ Online Review Data. / Kim, Sunghoon.

2018. Paper presented at 38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017, Seoul, Korea, Republic of.

Research output: Contribution to conferencePaper

Kim, S 2018, 'Integrated Machine-Learning Algorithm for Identifying Segment-Level Key Drivers from Consumers’ Online Review Data', Paper presented at 38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017, Seoul, Korea, Republic of, 12/10/17 - 12/13/17.
Kim S. Integrated Machine-Learning Algorithm for Identifying Segment-Level Key Drivers from Consumers’ Online Review Data. 2018. Paper presented at 38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017, Seoul, Korea, Republic of.
Kim, Sunghoon. / Integrated Machine-Learning Algorithm for Identifying Segment-Level Key Drivers from Consumers’ Online Review Data. Paper presented at 38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017, Seoul, Korea, Republic of.
@conference{12dd1693db004dafbd191a681a8434de,
title = "Integrated Machine-Learning Algorithm for Identifying Segment-Level Key Drivers from Consumers{\^a}€™ Online Review Data",
abstract = "I propose a newly integrated machine-learning methodology to apply a classic model-based segmentation method to unstructured online review data. The proposed algorithm extracts an independent variables matrix from unstructured textual reviews by developing a set of text-mining algorithms and then identifies segment-level key drivers by applying a proposed Bayesian ordinal probit mixture regression with variable selection. With the proposed method, firms can focus on key drivers per each segment in their marketing activities (e.g., online banner advertising, search advertising); this method will help them systematically keep track of periodic patterns of segment-level key drivers. Using online data from a large review site for rating professors, I validate the extracted independent variables through multiple validation studies and then show heterogeneous key drivers for satisfaction across three derived segments. For the least satisfied segment, the proportion of reviewers is significantly higher from the Science, Technology, Engineering, and Mathematics education category.",
keywords = "Machine learning, Market segmentation, Online textual reviews, Text mining, Variable selection",
author = "Sunghoon Kim",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
note = "38th International Conference on Information Systems: Transforming Society with Digital Innovation, ICIS 2017 ; Conference date: 10-12-2017 Through 13-12-2017",

}

TY - CONF

T1 - Integrated Machine-Learning Algorithm for Identifying Segment-Level Key Drivers from Consumers’ Online Review Data

AU - Kim, Sunghoon

PY - 2018/1/1

Y1 - 2018/1/1

N2 - I propose a newly integrated machine-learning methodology to apply a classic model-based segmentation method to unstructured online review data. The proposed algorithm extracts an independent variables matrix from unstructured textual reviews by developing a set of text-mining algorithms and then identifies segment-level key drivers by applying a proposed Bayesian ordinal probit mixture regression with variable selection. With the proposed method, firms can focus on key drivers per each segment in their marketing activities (e.g., online banner advertising, search advertising); this method will help them systematically keep track of periodic patterns of segment-level key drivers. Using online data from a large review site for rating professors, I validate the extracted independent variables through multiple validation studies and then show heterogeneous key drivers for satisfaction across three derived segments. For the least satisfied segment, the proportion of reviewers is significantly higher from the Science, Technology, Engineering, and Mathematics education category.

AB - I propose a newly integrated machine-learning methodology to apply a classic model-based segmentation method to unstructured online review data. The proposed algorithm extracts an independent variables matrix from unstructured textual reviews by developing a set of text-mining algorithms and then identifies segment-level key drivers by applying a proposed Bayesian ordinal probit mixture regression with variable selection. With the proposed method, firms can focus on key drivers per each segment in their marketing activities (e.g., online banner advertising, search advertising); this method will help them systematically keep track of periodic patterns of segment-level key drivers. Using online data from a large review site for rating professors, I validate the extracted independent variables through multiple validation studies and then show heterogeneous key drivers for satisfaction across three derived segments. For the least satisfied segment, the proportion of reviewers is significantly higher from the Science, Technology, Engineering, and Mathematics education category.

KW - Machine learning

KW - Market segmentation

KW - Online textual reviews

KW - Text mining

KW - Variable selection

UR - http://www.scopus.com/inward/record.url?scp=85041749199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041749199&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85041749199

ER -