Using Dependency Bigrams and Discourse Connectives for Predicting the Helpfulness of Online Reviews

11 Pages Posted: 26 Apr 2014

See all articles by Matthias Mertz

Matthias Mertz

Goethe University Frankfurt

Nikolaos Korfiatis

University of East Anglia (UEA) - Norwich Business School

Roberto Zicari

Goethe University Frankfurt

Date Written: April 24, 2014

Abstract

Helpfulness prediction of online consumer reviews is an interesting research topic with immediate practical applications both from a data mining and marketing perspective. As such a set of studies have been published in the last few years to tackle this problem, targeting the reviews' textual characteristics. In this paper, we propose and evaluate two text-based features that have not been used in the context of consumer review helpfulness prediction before. The first considers a variation of the bigram feature, utilizing grammatical dependencies instead of word adjacency. The second captures the type and amount of discourse in a text by looking for discourse connectives. In our experiments, we treat the helpfulness prediction problem as a binary classification task. The results show that both features contain valuable information for evaluating review helpfulness, however they should be used with caution due to the restrictive experimental setup. The study serves as a ground for future work regarding the usefulness of the proposed features in that perspective.

Keywords: Online reviews, Review helpfulness prediction, Text-based features, Feature engineering

Suggested Citation

Mertz, Matthias and Korfiatis, Nikolaos and Zicari, Roberto, Using Dependency Bigrams and Discourse Connectives for Predicting the Helpfulness of Online Reviews (April 24, 2014). Available at SSRN: https://ssrn.com/abstract=2428885 or http://dx.doi.org/10.2139/ssrn.2428885

Matthias Mertz

Goethe University Frankfurt ( email )

Gr├╝neburgplatz 1
Frankfurt am Main, 60323
Germany

Nikolaos Korfiatis (Contact Author)

University of East Anglia (UEA) - Norwich Business School ( email )

Norwich
NR4 7TJ
United Kingdom

Roberto Zicari

Goethe University Frankfurt ( email )

Gr├╝neburgplatz 1
Frankfurt am Main, 60323
Germany

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
63
Abstract Views
548
rank
360,744
PlumX Metrics