Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/www2010/paper/main/256> ?p ?o. }
Showing items 1 to 14 of
14
with 100 items per page.
- 256 creator alex-ntoulas.
- 256 creator livia-polanyi.
- 256 creator panayiotis-tsaparas.
- 256 creator yue-lu.
- 256 type InProceedings.
- 256 label "Exploiting Social Context for Review Quality Prediction".
- 256 sameAs 256.
- 256 abstract "Online reviews in which users publish detailed commentary on web portals about their experiences and opinions with products, services or events are extremely valuable to users who rely on them to make informed decisions. However, because reviews vary greatly in quality, automatic assessment of review helpfulness is of growing importance. Previous work has addressed the review quality prediction problem by treating a review as a stand-alone text document, extracting features from the review text, and learning a function based on these features for predicting the review quality. In this work, we exploit contextual information about authors' identity and social networks on top of review text features for review quality prediction. We propose a generic framework for incorporating social context information by adding novel regularization constraints to the text-based predictor. Our approach can effectively use the social context information available for large amount of unlabeled reviews. It also has the advantage that the resulting predictor is usable even if social context is unavailable. We validate our framework within a real commerce portal and experimentally demonstrate that using social contextual information can help improve the accuracy of review quality prediction especially when the available training data is sparse.".
- 256 hasAuthorList authorList.
- 256 isPartOf proceedings.
- 256 keyword "Use of social metadata".
- 256 keyword "annotations in search".
- 256 keyword "mining".
- 256 title "Exploiting Social Context for Review Quality Prediction".