TY - GEN
T1 - Ontology-Based Sentiment Analysis on News Title
AU - Kardinata, Eunike Andriani
AU - Rakhmawati, Nur Aini
AU - Zuhroh, Nurrida Aini
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/4/9
Y1 - 2021/4/9
N2 - News are one source of information that is easily accessible for the public. News can build an image of or shape the public opinion on the reported object. As such, news is an important medium in General Election (GE) for both the public and the candidates, to know what instruments are being put in place and how they fare. In this research, we performed an ontology-based sentiment analysis to find out whether the 2019 GE in Indonesia has received a positive or a negative response according to the different instruments used. We performed two kinds of experiment, one was based on lexicon and another was using Support Vector Machine (SVM) algorithm the results of our experiments show that SVM has a better classification performance. For lexicon-based method, the overall recall score was 28.8% and the overall precision score was 46.3%. Whereas for SVM-based method, the scores were 82.4% and 83.3% respectively these differences may be accounted for the fact that SVM considered our training input instead of just a fixed list of words.
AB - News are one source of information that is easily accessible for the public. News can build an image of or shape the public opinion on the reported object. As such, news is an important medium in General Election (GE) for both the public and the candidates, to know what instruments are being put in place and how they fare. In this research, we performed an ontology-based sentiment analysis to find out whether the 2019 GE in Indonesia has received a positive or a negative response according to the different instruments used. We performed two kinds of experiment, one was based on lexicon and another was using Support Vector Machine (SVM) algorithm the results of our experiments show that SVM has a better classification performance. For lexicon-based method, the overall recall score was 28.8% and the overall precision score was 46.3%. Whereas for SVM-based method, the scores were 82.4% and 83.3% respectively these differences may be accounted for the fact that SVM considered our training input instead of just a fixed list of words.
KW - general election
KW - lexicon
KW - sentiment
KW - support vector machine
UR - http://www.scopus.com/inward/record.url?scp=85107271836&partnerID=8YFLogxK
U2 - 10.1109/EIConCIT50028.2021.9431922
DO - 10.1109/EIConCIT50028.2021.9431922
M3 - Conference contribution
AN - SCOPUS:85107271836
T3 - 3rd 2021 East Indonesia Conference on Computer and Information Technology, EIConCIT 2021
SP - 360
EP - 364
BT - 3rd 2021 East Indonesia Conference on Computer and Information Technology, EIConCIT 2021
A2 - Alfred, Rayner
A2 - Haviluddin, Haviluddin
A2 - Wibawa, Aji Prasetya
A2 - Santoso, Joan
A2 - Kurniawan, Fachrul
A2 - Junaedi, Hartarto
A2 - Purnawansyah, Purnawansyah
A2 - Setyati, Endang
A2 - Saurik, Herman Thuan To
A2 - Setiawan, Esther Irawati
A2 - Setyaningsih, Eka Rahayu
A2 - Pramana, Edwin
A2 - Kristian, Yosi
A2 - Kelvin, Kelvin
A2 - Purwanto, Devi Dwi
A2 - Kardinata, Eunike
A2 - Anugrah, Prananda
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd East Indonesia Conference on Computer and Information Technology, EIConCIT 2021
Y2 - 9 April 2021 through 11 April 2021
ER -