Learning to Rank Items of Minimal Reviews using Weak Supervision

Shaalan, Y, Zhang, X and Chan, J 2018, 'Learning to Rank Items of Minimal Reviews using Weak Supervision', in Dinh Phung, Vincent S. Tseng, Geoffrey I. Webb, Bao Ho, Mohadeseh Ganji, Lida Rashidi (ed.) Proceedings of the 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2018) Part I, Melbourne, Australia, 3-6 June 2018, pp. 631-643.


Document type: Conference Paper
Collection: Conference Papers

Title Learning to Rank Items of Minimal Reviews using Weak Supervision
Author(s) Shaalan, Y
Zhang, X
Chan, J
Year 2018
Conference name PAKDD 2018: Lecture Notes in Artificial Intelligence Volume 10937
Conference location Melbourne, Australia
Conference dates 3-6 June 2018
Proceedings title Proceedings of the 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2018) Part I
Editor(s) Dinh Phung, Vincent S. Tseng, Geoffrey I. Webb, Bao Ho, Mohadeseh Ganji, Lida Rashidi
Publisher Springer
Place of publication Cham, Switzerland
Start page 631
End page 643
Total pages 13
Abstract Customer reviews and star ratings are widely used on E-commerce and reviewing sites for the public to express their opinions. To help the online public make decisions, items (e.g., products, services, movies, books) are typically represented and ordered by an aggregated star rating from all reviews. Existing approaches simply average star ratings or use other statistical functions to aggregate star ratings. However, these approaches rely on the existence of large numbers of reviews to work effectively. On the other hand, many new items have few reviews. In this paper, we argue that at the core of review aggregation is ranking items, hence, we cast the problem of ranking a set of items as a learning to rank (L2R) problem to address the issue of reviews scarcity. We devise a rank-oriented loss function to directly optimize the ranking of groups of items. Standard L2R models require ranking labels for training, but item ranking ground-truth information is not always available. Therefore, we propose to aggregate star ratings for items with large numbers of reviews to automatically generate weak supervision ranking labels for training. We further propose to extract features from review contents, rating distributions and helpfulness information to train the ranking model. Extensive experiments on an Amazon dataset showed that our model is very effective compared to state-of-the-art heuristic aggregation approaches, regression and standard L2R approaches.
Subjects Pattern Recognition and Data Mining
Keyword(s) Ranking
learning to rank
weak supervision
DOI - identifier 10.1007/978-3-319-93034-3_50
Copyright notice © Springer International Publishing AG, part of Springer Nature 2018
ISBN 9783319930336
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 34 Abstract Views  -  Detailed Statistics
Created: Thu, 06 Dec 2018, 10:39:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us