Using Argument-based Features to Predict and Analyse Review Helpfulness

Haijing Liu; Yang Gao; Ping Lv; Mengxue Li; Shiqiang Geng; Minglan Li; Hao Wang

doi:10.18653/v1/D17-1142

Using Argument-based Features to Predict and Analyse Review Helpfulness

Haijing Liu, Yang Gao, Ping Lv, Mengxue Li, Shiqiang Geng, Minglan Li, Hao Wang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We study the helpful product reviews identification problem in this paper. We observe that the evidence-conclusion discourse relations, also known as arguments, often appear in product reviews, and we hypothesise that some argument-based features, e.g. the percentage of argumentative sentences, the evidences-conclusions ratios, are good indicators of helpful reviews. To validate this hypothesis, we manually annotate arguments in 110 hotel reviews, and investigate the effectiveness of several combinations of argument-based features. Experiments suggest that, when being used together with the argument-based features, the state-of-the-art baseline features can enjoy a performance boost (in terms of F1) of 11.01% in average.

Original language	English
Title of host publication	Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Place of Publication	Copenhagen, Denmark
Publisher	Association for Computational Linguistics
Pages	1358–1363
Number of pages	6
DOIs	https://doi.org/10.18653/v1/D17-1142
Publication status	Published - Sept 2017

Access to Document

10.18653/v1/D17-1142

https://aclweb.org/anthology/papers/D/D17/D17-1142/

Cite this

@inproceedings{37b56e972cb440d7b0d30e6d93c668c2,

title = "Using Argument-based Features to Predict and Analyse Review Helpfulness",

abstract = "We study the helpful product reviews identification problem in this paper. We observe that the evidence-conclusion discourse relations, also known as arguments, often appear in product reviews, and we hypothesise that some argument-based features, e.g. the percentage of argumentative sentences, the evidences-conclusions ratios, are good indicators of helpful reviews. To validate this hypothesis, we manually annotate arguments in 110 hotel reviews, and investigate the effectiveness of several combinations of argument-based features. Experiments suggest that, when being used together with the argument-based features, the state-of-the-art baseline features can enjoy a performance boost (in terms of F1) of 11.01\% in average.",

author = "Haijing Liu and Yang Gao and Ping Lv and Mengxue Li and Shiqiang Geng and Minglan Li and Hao Wang",

year = "2017",

month = sep,

doi = "10.18653/v1/D17-1142",

language = "English",

pages = "1358–1363",

booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",

publisher = "Association for Computational Linguistics",

}

Using Argument-based Features to Predict and Analyse Review Helpfulness. / Liu, Haijing; Gao, Yang; Lv, Ping et al.
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen, Denmark: Association for Computational Linguistics, 2017. p. 1358–1363.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Using Argument-based Features to Predict and Analyse Review Helpfulness

AU - Liu, Haijing

AU - Gao, Yang

AU - Lv, Ping

AU - Li, Mengxue

AU - Geng, Shiqiang

AU - Li, Minglan

AU - Wang, Hao

PY - 2017/9

Y1 - 2017/9

N2 - We study the helpful product reviews identification problem in this paper. We observe that the evidence-conclusion discourse relations, also known as arguments, often appear in product reviews, and we hypothesise that some argument-based features, e.g. the percentage of argumentative sentences, the evidences-conclusions ratios, are good indicators of helpful reviews. To validate this hypothesis, we manually annotate arguments in 110 hotel reviews, and investigate the effectiveness of several combinations of argument-based features. Experiments suggest that, when being used together with the argument-based features, the state-of-the-art baseline features can enjoy a performance boost (in terms of F1) of 11.01% in average.

AB - We study the helpful product reviews identification problem in this paper. We observe that the evidence-conclusion discourse relations, also known as arguments, often appear in product reviews, and we hypothesise that some argument-based features, e.g. the percentage of argumentative sentences, the evidences-conclusions ratios, are good indicators of helpful reviews. To validate this hypothesis, we manually annotate arguments in 110 hotel reviews, and investigate the effectiveness of several combinations of argument-based features. Experiments suggest that, when being used together with the argument-based features, the state-of-the-art baseline features can enjoy a performance boost (in terms of F1) of 11.01% in average.

U2 - 10.18653/v1/D17-1142

DO - 10.18653/v1/D17-1142

M3 - Conference contribution

SP - 1358

EP - 1363

BT - Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics

CY - Copenhagen, Denmark

ER -