Cross-Domain Sentiment Classification via Topic-Related TrAdaBoost

Xingchang Huang, Yanghui Rao, Haoran Xie, Tak-Lam Wong, Fu Lee Wang

AAAI 2017 pp. 4939-4940

doi:10.1609/AAAI.V31I1.11099 /aaai/2017/huang2017aaai-cross/

Abstract

Cross-domain sentiment classification aims to tag sentiments for a target domain by labeled data from a source domain. Due to the difference between domains, the accuracy of a trained classifier may be very low. In this paper, we propose a boosting-based learning framework named TR-TrAdaBoost for cross-domain sentiment classification. We firstly explore the topic distribution of documents, and then combine it with the unigram TrAdaBoost. The topic distribution captures the domain information of documents, which is valuable for cross-domain sentiment classification. Experimental results indicate that TR-TrAdaBoost represents documents well and boost the performance and robustness of TrAdaBoost.

PDF AAAI Semantic Scholar

Cite

Text

Huang et al. "Cross-Domain Sentiment Classification via Topic-Related TrAdaBoost." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.11099

Markdown

[Huang et al. "Cross-Domain Sentiment Classification via Topic-Related TrAdaBoost." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/huang2017aaai-cross/) doi:10.1609/AAAI.V31I1.11099

BibTeX

@inproceedings{huang2017aaai-cross,
  title     = {{Cross-Domain Sentiment Classification via Topic-Related TrAdaBoost}},
  author    = {Huang, Xingchang and Rao, Yanghui and Xie, Haoran and Wong, Tak-Lam and Wang, Fu Lee},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {4939-4940},
  doi       = {10.1609/AAAI.V31I1.11099},
  url       = {https://mlanthology.org/aaai/2017/huang2017aaai-cross/}
}