More Is Better: Large Scale Partially-supervised Sentiment Classification

Yoav Haimovitch, Koby Crammer, Shie Mannor
Proceedings of the Asian Conference on Machine Learning, PMLR 25:175-190, 2012.

Abstract

We describe a bootstrapping algorithm to learn from partially labeled data, and the results of an empirical study for using it to improve performance of sentiment classification using up to 15 million unlabeled Amazon product reviews. Our experiments cover semi-supervised learning, domain adaptation and weakly supervised learning. In some cases our methods were able to reduce test error by more than half using such large amount of data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v25-haimovitch12, title = {More Is Better: Large Scale Partially-supervised Sentiment Classification}, author = {Haimovitch, Yoav and Crammer, Koby and Mannor, Shie}, booktitle = {Proceedings of the Asian Conference on Machine Learning}, pages = {175--190}, year = {2012}, editor = {Hoi, Steven C. H. and Buntine, Wray}, volume = {25}, series = {Proceedings of Machine Learning Research}, address = {Singapore Management University, Singapore}, month = {04--06 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v25/haimovitch12/haimovitch12.pdf}, url = {https://proceedings.mlr.press/v25/haimovitch12.html}, abstract = {We describe a bootstrapping algorithm to learn from partially labeled data, and the results of an empirical study for using it to improve performance of sentiment classification using up to 15 million unlabeled Amazon product reviews. Our experiments cover semi-supervised learning, domain adaptation and weakly supervised learning. In some cases our methods were able to reduce test error by more than half using such large amount of data.} }
Endnote
%0 Conference Paper %T More Is Better: Large Scale Partially-supervised Sentiment Classification %A Yoav Haimovitch %A Koby Crammer %A Shie Mannor %B Proceedings of the Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2012 %E Steven C. H. Hoi %E Wray Buntine %F pmlr-v25-haimovitch12 %I PMLR %P 175--190 %U https://proceedings.mlr.press/v25/haimovitch12.html %V 25 %X We describe a bootstrapping algorithm to learn from partially labeled data, and the results of an empirical study for using it to improve performance of sentiment classification using up to 15 million unlabeled Amazon product reviews. Our experiments cover semi-supervised learning, domain adaptation and weakly supervised learning. In some cases our methods were able to reduce test error by more than half using such large amount of data.
RIS
TY - CPAPER TI - More Is Better: Large Scale Partially-supervised Sentiment Classification AU - Yoav Haimovitch AU - Koby Crammer AU - Shie Mannor BT - Proceedings of the Asian Conference on Machine Learning DA - 2012/11/17 ED - Steven C. H. Hoi ED - Wray Buntine ID - pmlr-v25-haimovitch12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 25 SP - 175 EP - 190 L1 - http://proceedings.mlr.press/v25/haimovitch12/haimovitch12.pdf UR - https://proceedings.mlr.press/v25/haimovitch12.html AB - We describe a bootstrapping algorithm to learn from partially labeled data, and the results of an empirical study for using it to improve performance of sentiment classification using up to 15 million unlabeled Amazon product reviews. Our experiments cover semi-supervised learning, domain adaptation and weakly supervised learning. In some cases our methods were able to reduce test error by more than half using such large amount of data. ER -
APA
Haimovitch, Y., Crammer, K. & Mannor, S.. (2012). More Is Better: Large Scale Partially-supervised Sentiment Classification. Proceedings of the Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 25:175-190 Available from https://proceedings.mlr.press/v25/haimovitch12.html.

Related Material