Structural Correspondence Learning for Cross-Domain Sentiment Analysis in Brazilian Portuguese

Over the years, many approaches to the cross-domain task in Sentiment Analysis have been proposed. The vast majority of such approaches concerns corpora in English language. Following a different methodology, this paper proposes three novel product review datasets written in Brazilian Portuguese. These datasets are freely available and they cannot only be used as benchmark datasets by other researchers, but also to perform domain adaptation comparative assessments. In addition, the entire creation process for the proposed datasets is described. Another contribution resides in the first experimental evaluation of the state-of-the-art algorithm Structural Correspondence Learning (SCL) on cross-domain sentiment analysis (domain adaption). Furthermore, two other variants of the original SCL algorithm are evaluated on the proposed datasets and their performance are compared against each other.

[1]  John Blitzer,et al.  Domain Adaptation with Structural Correspondence Learning , 2006, EMNLP.

[2]  Henrico Bertini Brum,et al.  PELESent: Cross-Domain Polarity Classification Using Distant Supervision , 2017, 2017 Brazilian Conference on Intelligent Systems (BRACIS).

[3]  Xuanjing Huang,et al.  Cross-Domain Sentiment Classification with Target Domain Specific Information , 2018, ACL.

[4]  Zhongfei Zhang,et al.  Structural Correspondence Learning for Cross-Lingual Sentiment Classification with One-to-Many Mappings , 2016, AAAI.

[5]  Ngo Xuan Bach,et al.  Cross-domain sentiment classification with word embeddings and canonical correlation analysis , 2016, SoICT.

[6]  Salwani Abdullah,et al.  Approaches to Cross-Domain Sentiment Analysis: A Systematic Literature Review , 2017, IEEE Access.

[7]  Qiang Yang,et al.  Cross-domain sentiment classification via spectral feature alignment , 2010, WWW '10.

[8]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[9]  Chang Zhou,et al.  Domain Adaptation Approach for Sentiment Analysis , 2019, ICCDA 2019.

[10]  Danushka Bollegala,et al.  Cross-Domain Sentiment Classification Using Sentiment Sensitive Embeddings , 2016, IEEE Transactions on Knowledge and Data Engineering.

[11]  Danushka Bollegala,et al.  Cross-Domain Sentiment Classification Using a Sentiment Sensitive Thesaurus , 2013, IEEE Transactions on Knowledge and Data Engineering.

[12]  Zhen Zuo.  Sentiment Analysis of Steam Review Datasets using Naive Bayes and Decision Tree Classifier , 2018 .

[13]  Sonali Agarwal,et al.  Cross domain sentiment analysis using transfer learning , 2017, 2017 IEEE International Conference on Industrial and Information Systems (ICIIS).

[14]  Hsin-Hsi Chen,et al.  Exploring Ensemble of Models in Taxonomy-based Cross-Domain Sentiment Classification , 2014, CIKM.

[15]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[16]  Yoshua Bengio,et al.  Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach , 2011, ICML.

[17]  Roi Reichart,et al.  Neural Structural Correspondence Learning for Domain Adaptation , 2016, CoNLL.

[18]  Adel Said Elmaghraby,et al.  Deep Learning Based vs. Markov Chain Based Text Generation for Cross Domain Adaptation for Sentiment Classification , 2018, 2018 IEEE International Conference on Information Reuse and Integration (IRI).

[19]  Benno Stein,et al.  Cross-Language Text Classification Using Structural Correspondence Learning , 2010, ACL.

[20]  Songbo Tan,et al.  Improving SCL Model for Sentiment-Transfer Learning , 2009, HLT-NAACL.

[21]  Alcione de Paiva Oliveira,et al.  Development of a Brazilian Portuguese Hotel's Reviews Corpus , 2018, PROPOR.