Skip navigation
User training | Reference and search service

Library catalog

Content aggregators
Please use this identifier to cite or link to this item:

Title: Rating prediction on yelp academic dataset using paragraph vectors
Authors: Maia, R.
Ferreira, J.
Martins, A.
Keywords: Prediction
Paragraph vectors
Dimension reduce
Issue Date: 2019
Publisher: IIER
Abstract: This work studies the application of Paragraph Vectors to the Yelp Academic Dataset reviews in order to predict user ratings for different categories of businesses like auto repair, restaurants or veterinarians. Paragraph Vectors is a word embeddings techniques were each word or piece of text is converted to a continuous low dimensional space. Then, the opinion mining or sentiment analysis is observed as a classification task, where each user review is associated with a label the rating - and a probabilistic model is built with a logistic classifier. Following the intuition that the semantic information present in textual user reviews is generally more complex and complete than the numeric rating itself, this work applies Paragraph Vectors successfully toYelp dataset and evaluates its results.
Peer reviewed: yes
ISSN: 2348-7437
Appears in Collections:BRU-CRI - Comunicações a conferências internacionais
ISTAR-CRI - Comunicações a conferências internacionais

Files in This Item:
File Description SizeFormat 
2815-156197466656-62.pdfPós-print426.68 kBAdobe PDFView/Open

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Currículo DeGóis 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.