TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Liu, Can
A1  - Guo, Chun
A1  - Dakota, Daniel
A1  - Rajagopalan, Sridhar
A1  - Li, Wen
A1  - Kübler, Sandra
A1  - Yu, Ning
ED  - Lin, Shou-de
ED  - Ku, Lun-Wei
ED  - Cambria, Erik
ED  - Kuo, Tsung-Ting
T1  - “My Curiosity was Satisfied, but not in a Good Way”: Predicting User Ratings for Online Recipes
T2  - Proceedings of the Second Workshop on Natural Language Processing for Social Media in conjunction with COLING-2014 (SocialNLP 2014). Dublin, Ireland. August 24, 2014
N2  - 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%.
KW  - Propositionale Einstellung
KW  - Information Extraction
KW  - Kochbuch
KW  - Internet
KW  - Sentiment analysis
Y1  - 2014
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-61863
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-61863
UR  - http://www.aclweb.org/anthology/W/W14/#5900
SN  - 978-1-873769-45-4
SB  - 978-1-873769-45-4
SP  - 12
EP  - 21
ER  -