A Penalized Neural Network Model for Predicting Unobserved Scores of Construct Indicators and Reproducing Latent Scores of the Theoretical Constructs by Using Text Information

Toshikuni Sato ()
Additional contact information
Toshikuni Sato: Meiji University

Chapter Chapter 1 in City, Society, and Digital Transformation, 2022, pp 1-14 from Springer

Abstract: Abstract This paper discusses a novel application of construct measurement with a penalized neural network in a text analysis. Conducting a survey with the measures of constructs is a traditional approach to scoring customers’ mental states, such as feelings, perceptions, and attitudes. Numerous types of scales are continuously developed for marketing and consumer behavior research. To connect this traditional methodology with machine learning and big data analysis, our proposed neural network model uses two penalty functions, which specify the confirmatory factor model as a measurement equation. In the empirical analysis, the proposed model shows stable parameter estimates compared with a standard unconstrained neural network and supports theoretical interpretations. By applying the learned proposed model, predictive item scores of each questionnaire and alternative scores of theoretical constructs can be obtained through text information. The proposed methodology helps marketers and researchers visualize consumers’ representations of perceived theoretical constructs without the survey. To enhance the proposed model’s accuracy and validity, limitations and potential works are also discussed for future study.

Keywords: Penalized neural network; Construct measurement; Text analysis; Parameter identification (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-3-031-15644-1_1

Ordering information: This item can be ordered from
http://www.springer.com/9783031156441

DOI: 10.1007/978-3-031-15644-1_1

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().