Preprocessing impact on Turkish sentiment analysis

This paper investigates the impact of preprocessing on sentiment classification of Turkish movies and products reviews. Input datasets were subjected to several combinations of preprocessing techniques. Later, the manipulated reviews were fed to a lexicon-based and a supervised machine learning sent...

Full description

Saved in:
Bibliographic Details
Published in2018 26th Signal Processing and Communications Applications Conference (SIU) pp. 1 - 4
Main Authors Mulki, Hala, Haddad, Hatem, Ali, Chedi Bechikh, Babaoglu, Ismail
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2018
Subjects
Data models
lexicon-based sentiment classifier
Motion pictures
Predictive models
Preprocessing
Sentiment analysis
supervised sentiment classifier
Support vector machines
Task analysis
Training
Turkish sentiment analysis
Online AccessGet full text

Cover

More Information
Summary:This paper investigates the impact of preprocessing on sentiment classification of Turkish movies and products reviews. Input datasets were subjected to several combinations of preprocessing techniques. Later, the manipulated reviews were fed to a lexicon-based and a supervised machine learning sentiment classifiers. The achieved results emphasize the positive impact of preprocessing phase on the accuracy of both sentiment classifiers as the baseline was outperformed with a considerable margin especially when stemming, emoji recognition and negation detection tasks were applied.
DOI:10.1109/SIU.2018.8404718