Prediction of Opinion Keywords and Their Sentiment Strength Score Using Latent Space Learning Methods

Simple item page
dc.contributor.authorGarcía Cuesta, Esteban
dc.contributor.authorGómez Vergel, Daniel
dc.contributor.authorGracia Expósito, Luis
dc.contributor.authorLópez López, Jose M.
dc.contributor.authorVela Pérez, María
dc.date.accessioned2023-06-17T09:11:27Z
dc.date.available2023-06-17T09:11:27Z
dc.date.issued2020-06-18
dc.description.abstractMost item-shopping websites give people the opportunity to express their thoughts and opinions on items available for purchasing. This information often includes both ratings and text reviews expressing somehow their tastes and can be used to predict their future opinions on items not yet reviewed. Whereas most recommendation systems have focused exclusively on ranking the items based on rating predictions or user-modeling approaches, we propose an adapted recommendation system based on the prediction of opinion keywords assigned to different item characteristics and their sentiment strength scores. This proposal makes use of natural language processing (NLP) tools for analyzing the text reviews and is based on the assumption that there exist common user tastes which can be represented by latent review topics models. This approach has two main advantages: is able to predict interpretable textual keywords and its associated sentiment (positive/negative) which will help to elaborate a more precise recommendation and justify it, and allows the use of different dictionary sizes to balance performance and user opinion interpretability. To prove the feasibility of the adapted recommendation system, we have tested the capabilities of our method to predict the sentiment strength score of item characteristics not previously reviewed. The experimental results have been performed with real datasets and the obtained F1 score ranges from 66% to 77% depending on the dataset used. Moreover, the results show that the method can generalize well and can be applied to combined domain independent datasets.
dc.description.departmentDepto. de Economía Financiera y Actuarial y Estadística
dc.description.facultyFac. de Ciencias Económicas y Empresariales
dc.description.refereedTRUE
dc.description.sponsorshipMinisterio de Economía y Competitividad (MINECO)
dc.description.sponsorshipUniversidad Europea de Madrid
dc.description.statuspub
dc.eprint.idhttps://eprints.ucm.es/id/eprint/67519
dc.identifier.doi10.3390/app10124196
dc.identifier.issn2076-3417
dc.identifier.officialurlhttps://doi.org/10.3390/app10124196
dc.identifier.relatedurlhttps://www.mdpi.com/2076-3417/10/12/4196
dc.identifier.urihttps://hdl.handle.net/20.500.14352/8362
dc.issue.number12
dc.journal.titleApplied Sciences
dc.language.isoeng
dc.page.initial4196
dc.publisherMDPI
dc.relation.projectIDMTM2014-57158-R
dc.relation.projectIDE-Modelo project
dc.rightsAtribución 3.0 España
dc.rights.accessRightsopen access
dc.rights.urihttps://creativecommons.org/licenses/by/3.0/es/
dc.subject.keywordOpinion mining
dc.subject.keywordtext mining
dc.subject.keywordrecommendation systems
dc.subject.keywordsentiment strength prediction
dc.subject.keywordlatent models
dc.subject.ucmInvestigación Comercial
dc.subject.ucmComercio
dc.subject.unesco5304.03 Comercio exterior
dc.titlePrediction of Opinion Keywords and Their Sentiment Strength Score Using Latent Space Learning Methods
dc.typejournal article
dc.volume.number10
dspace.entity.typePublication
relation.isAuthorOfPublicationb52fb0a2-f0de-4c28-b0ac-995df1bd113f
relation.isAuthorOfPublication.latestForDiscoveryb52fb0a2-f0de-4c28-b0ac-995df1bd113f
Download
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
applsci-10-04196-v2.pdf
Size:
1.66 MB
Format:
Adobe Portable Document Format
downoload Download
Collections
Artículos