The Text-Score Allocation Model: Finding Latent Topics of Online Review Documents and Multi-Item Ratings

Sotaro Katsumata () and Seungjin Kim
Additional contact information
Sotaro Katsumata: Graduate School of Economics, Osaka University
Seungjin Kim: Graduate School of Economics, Osaka University

No 20-01, Discussion Papers in Economics and Business from Osaka University, Graduate School of Economics

Abstract: This studyfocusesononlinereviewdatainwhichcommentsarewritteninnaturallanguages and evaluationsareattachedasintegers.Thisstudydevelopsatopicmodelincorporatingboth natural languagesandevaluationscores,expandinglatentDirichletallocation(LDA).Themodel consists oftwocomponents:LDAandaDirichlet-binomialclusteringmodel.Thelatterassumes binomial distributionsforthereviewscores.Sincethemodelassumesconjugatedistributions,we can applyafastandstableestimatorbasedoncollapsedGibbssamplingtoestimatetheparameters. Further,themodelenablesustoexaminetherelationshipbetweenvocabularywordsandreview scores basedonthetopicallocationresults.

Keywords: TopicModeling; CustomerReviews; Forecasting (search for similar items in EconPapers)
Pages: 36 pages
Date: 2020-01
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www2.econ.osaka-u.ac.jp/econ_society/dp/2001.pdf (application/pdf)

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:osk:wpaper:2001

Access Statistics for this paper

More papers in Discussion Papers in Economics and Business from Osaka University, Graduate School of Economics Contact information at EDIRC.
Bibliographic data for series maintained by The Economic Society of Osaka University ().