Volltext-Downloads (blau) und Frontdoor-Views (grau)

“My Curiosity was Satisfied, but not in a Good Way”: Predicting User Ratings for Online Recipes

  • In this paper, we develop an approach to automatically predict user ratings for recipes at Epicurious.com, based on the recipes’ reviews. We investigate two distributional methods for feature selection, Information Gain and Bi-Normal Separation; we also compare distributionally selected features to linguistically motivated features and two types of frameworks: a one-layer system where we aggregate all reviews and predict the rating vs. a two-layer system where ratings of individual reviews are predicted and then aggregated. We obtain our best results by using the two-layer architecture, in combination with 5 000 features selected by Information Gain. This setup reaches an overall accuracy of 65.60%, given an upper bound of 82.57%.

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Can Liu, Chun Guo, Daniel Dakota, Sridhar Rajagopalan, Wen Li, Sandra Kübler, Ning Yu
URN:urn:nbn:de:bsz:mh39-61863
URL:http://www.aclweb.org/anthology/W/W14/#5900
ISBN:978-1-873769-45-4
Parent Title (English):Proceedings of the Second Workshop on Natural Language Processing for Social Media in conjunction with COLING-2014 (SocialNLP 2014). Dublin, Ireland. August 24, 2014
Editor:Shou-de Lin, Lun-Wei Ku, Erik Cambria, Tsung-Ting Kuo
Document Type:Conference Proceeding
Language:English
Year of first Publication:2014
Date of Publication (online):2017/05/23
Publicationstate:Veröffentlichungsversion
Reviewstate:Peer-Review
Tag:Sentiment analysis
GND Keyword:Information Extraction; Internet; Kochbuch; Propositionale Einstellung
First Page:12
Last Page:21
DDC classes:400 Sprache / 400 Sprache, Linguistik
Open Access?:ja
Linguistics-Classification:Computerlinguistik
Licence (English):License LogoCreative Commons - Attribution 4.0 International