Predicting usefulness of Yelp reviews with localized linear regression models

Ruhui Shen, Jialiang Shen, Yuhong Li, Haohan Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Many websites such as Yelp provide platform for users to write reviews about places they have visited. But not all reviews are equally useful. However, it generally takes from several weeks to months to receive feedback about 'usefulness' of review from online community. So there is a need to automatically predict the 'usefulness' of review. In this paper, we are trying to solve the specific question 'How many 'useful' votes a Yelp review will receive?' by using bag-of-words, linguistic, geographical, statistical, popularity and other qualitative features extracted from user, business and review information provided by Yelp. We use state-of-The-Art machine learning algorithms for regression to predict required numeric value of 'usefulness' of review. We further gained performance improvement by introducing a batch mode localized weighted regression model. This localized regression approach resulted into RMSLE of 0.47769, which is better than traditional methods.

Original languageEnglish (US)
Title of host publicationICSESS 2016 - Proceedings of 2016 IEEE 7th International Conference on Software Engineering and Service Science
EditorsM. Surendra Prasad Babu, Li Wenzheng
PublisherIEEE Computer Society
Pages189-192
Number of pages4
ISBN (Electronic)9781467399036
DOIs
StatePublished - Jul 2 2016
Externally publishedYes
Event7th IEEE International Conference on Software Engineering and Service Science, ICSESS 2016 - Beijing, China
Duration: Aug 26 2016Aug 28 2016

Publication series

NameProceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS
Volume0
ISSN (Print)2327-0586
ISSN (Electronic)2327-0594

Conference

Conference7th IEEE International Conference on Software Engineering and Service Science, ICSESS 2016
Country/TerritoryChina
CityBeijing
Period8/26/168/28/16

Keywords

  • linear regression
  • localized model
  • machine learning

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'Predicting usefulness of Yelp reviews with localized linear regression models'. Together they form a unique fingerprint.

Cite this