Improving the quality of predictions using textual information in online user reviews

157 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Aspect Based Recommendations: Recommending Items with the Most Valuable Aspects Based on User Reviews (2017, background): “For example, the authors of [10] found six aspects in restaurant reviews and trained classiers to identify them in the review to improve rating prediction quality.”
Exploring demographic information in social media for product recommendation (2015, background): “([42]) derived text-based ratings of item aspects from review text and then grouped similar users together based on the topics and sentiments that appear in the reviews.”
Recommender systems based on user reviews: the state of the art (2015, methodology): “The first sub-branch shows that systems incorporating aspect opinions (i.e., 〈aspect, sentiment〉 pairs) achieve better prediction accuracy than the ones that only consider overall ratings (Ganu et al. 2013; Jakob et al. 2009; Wang et al. 2012).”