IDENTIFYING POLARITY IN DIFFERENT TEXT TYPES

被引:6
作者
Pajupuu, Hille
Altrov, Rene
Pajupuu, Jaan
机构
[1] Institute of the Estonian Language, Tallinn
关键词
lexicon-based approach; machine learning approach; Naive Bayes; polarity; sentiment analysis; SVM; text types; SENTIMENT ANALYSIS; SUBJECTIVITY;
D O I
10.7592/FEJF2016.64.polarity
中图分类号
I27 [民间文学];
学科分类号
030304 ;
摘要
While Sentiment Analysis aims to identify the writer's attitude toward individuals, events or topics, our aim is to predict the possible effect of a written text on the reader. For this purpose, we created an automatic identifier of the polarity of Estonian texts, which is independent of domain and of text type. Depending on the approach chosen - lexicon-based or machine learning - the identifier uses either a lexicon of words with a positive or negative connotation, or a text corpus where orthographic paragraphs have been annotated as positive, negative, neutral or mixed. Both approaches worked well, resulting in a nearly 75% accuracy on average. It was found that in some cases the results depend on the text type, notably, with sports texts the lexicon-based approach yielded a maximum accuracy of 80.3%, while over 88% was gained for opinion stories approached by machine learning.
引用
收藏
页码:125 / 142
页数:18
相关论文
共 22 条
[1]   SAMAR: Subjectivity and sentiment analysis for Arabic social media [J].
Abdul-Mageed, Muhammad ;
Diab, Mona ;
Kuebler, Sandra .
COMPUTER SPEECH AND LANGUAGE, 2014, 28 (01) :20-37
[2]  
[Anonymous], 2015, INT J COMPUTER APPL, DOI DOI 10.5120/IJCA2015907218
[3]   Computational approaches to subjectivity and sentiment analysis: Present and envisaged methods and applications [J].
Balahur, Alexandra ;
Mihalcea, Rada ;
Montoyo, Andres .
COMPUTER SPEECH AND LANGUAGE, 2014, 28 (01) :1-6
[4]  
Bo P., 2008, Foundations and Trends in Information Retrieval, V2, P1, DOI DOI 10.1561/1500000011
[5]  
Kerge Krista, 2014, P TALL U I EST LANG, V16, P103
[6]   Towards a unified framework for opinion retrieval, mining and summarization [J].
Lloret, Elena ;
Balahur, Alexandra ;
Gomez, Jose M. ;
Montoyo, Andres ;
Palomar, Manuel .
JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2012, 39 (03) :711-747
[7]  
Mohammad Saif., 2009, P 2009 C EMPIRICAL M, P599, DOI DOI 10.3115/1699571.1699591
[8]   Subjectivity and sentiment analysis: An overview of the current state of the area and envisaged developments [J].
Montoyo, Andres ;
Martinez-Barco, Patricio ;
Balahur, Alexandra .
DECISION SUPPORT SYSTEMS, 2012, 53 (04) :675-679
[9]   LEXICON-BASED DETECTION OF EMOTION IN DIFFERENT TYPES OF TEXTS: PRELIMINARY REMARKS [J].
Pajupuu, Hille ;
Kerge, Krista ;
Altrov, Rene .
EESTI RAKENDUSLINGVISTIKA UHINGU AASTARAAMAT, 2012, 8 :171-184
[10]  
Pajupuu Hille, 2012, COLLECCION AQUILAFUE, V185, P229