Using Argument-based Features to Predict and Analyse Review Helpfulness
This work addresses the problem of filtering helpful reviews for consumers and platforms, but it is incremental as it builds on existing baseline features with a modest performance gain.
The paper tackled the problem of identifying helpful product reviews by hypothesizing that argument-based features, such as the percentage of argumentative sentences and evidence-conclusion ratios, are good indicators. Experiments on 110 manually annotated hotel reviews showed that combining these features with state-of-the-art baselines boosted F1 performance by an average of 11.01%.
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.