GANs for Semi-Supervised Opinion Spam Detection
Abstract
Online reviews have become a vital source of information in purchasing a service (product). Opinion spammers manipulate reviews, affecting the overall perception of the service. A key challenge in detecting opinion spam is obtaining ground truth. Though there exists a large set of reviews, only a few of them have been labeled spam or non-spam. We propose spamGAN, a generative adversarial network which relies on limited labeled data as well as unlabeled data for opinion spam detection. spamGAN improves the state-of-the-art GAN based techniques for text classification. Experiments on TripAdvisor data show that spamGAN outperforms existing techniques when labeled data is limited. spamGAN can also generate reviews with reasonable perplexity.
Cite
Text
Stanton and Irissappane. "GANs for Semi-Supervised Opinion Spam Detection." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/723Markdown
[Stanton and Irissappane. "GANs for Semi-Supervised Opinion Spam Detection." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/stanton2019ijcai-gans/) doi:10.24963/IJCAI.2019/723BibTeX
@inproceedings{stanton2019ijcai-gans,
title = {{GANs for Semi-Supervised Opinion Spam Detection}},
author = {Stanton, Gray and Irissappane, Athirai Aravazhi},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2019},
pages = {5204-5210},
doi = {10.24963/IJCAI.2019/723},
url = {https://mlanthology.org/ijcai/2019/stanton2019ijcai-gans/}
}