An opinion mining approach for Romanian language

Author

Russu, Roxana Monica ; Vlad, Oana Luminita ; Dinsoreanu, Mihaela ; Potolea, Rodica

Author_Institution

Tech. Univ. of Cluj-Napoca, Cluj-Napoca, Romania

fYear

2014

fDate

4-6 Sept. 2014

Firstpage

43

Lastpage

46

Abstract

The paper proposes a solution for document and aspect levels sentiment analysis for unstructured documents written in the Romanian language. The opinion extraction relies on two different approaches for polarity identification. At the aspect level we propose a rule-based approach. For the document level we consider supervised learning techniques, based on features extracted and filtered in different layers, based on their polarity discriminative power.

Keywords

data mining; knowledge based systems; learning (artificial intelligence); natural language processing; Romanian language; aspect level sentiment analysis; document analysis; feature extraction; opinion extraction; opinion mining; polarity identification; rule-based approach; supervised learning; Classification algorithms; Educational institutions; Feature extraction; Niobium; Search engines; Support vector machines; Text categorization; NLP; Romanian; implementation; machine learning; opinion mining;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computer Communication and Processing (ICCP), 2014 IEEE International Conference on

Conference_Location

Cluj Napoca

Print_ISBN

978-1-4799-6568-7

Type

conf

DOI

10.1109/ICCP.2014.6936978

Filename

6936978