Unsupervised Methods to Improve Aspect-Based Sentiment Analysis in Czech

Tomáš Hercig, Tomáš Brychcín, Lukáš Svoboda, Michal Konkol, Josef Steinberger


We examine the effectiveness of several unsupervised methods for latent semantics discovery as features for aspect-based sentiment analysis (ABSA). We use the shared task definition from SemEval 2014. In our experiments we use labeled and unlabeled corpora within the restaurants domain for two languages: Czech and English. We show that our models improve the ABSA performance and prove that our approach is worth exploring. Moreover, we achieve new state-of-the-art results for Czech. Another important contribution of our work is that we created two new Czech corpora within the restaurant domain for the ABSA task: one labeled for supervised training, and the other (considerably larger) unlabeled for unsupervised training. The corpora are available to the research community.


Aspect-based sentiment analysis, latent semantics.

Full Text: PDF