You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We propose to augment rating based recommender systems by providing the userwith additional information which might help him in his choice or in theunderstanding of the recommendation. We consider here as a new task, thegeneration of personalized reviews associated to items. We use an extractivesummary formulation for generating these reviews. We also show that the twoinformation sources, ratings and items could be used both for estimatingratings and for generating summaries, leading to improved performance for eachsystem compared to the use of a single source. Besides these two contributions,we show how a personalized polarity classifier can integrate the rating andtextual aspects. Overall, the proposed system offers the user threepersonalized hints for a recommendation: rating, text and polarity. We evaluatethese three components on two datasets using appropriate measures for eachtask.
AkihikoWatanabe
changed the title
a
Extended Recommendation Framework: Generating the Text of a User Review
as a Personalized Summary, Mickaël Poussevin+, N/A, arXiv'14
May 5, 2023
URL
Affiliations
Abstract
Translation (by gpt-3.5-turbo)
Summary (by gpt-3.5-turbo)
The text was updated successfully, but these errors were encountered: