TY - GEN
T1 - Analysis of convolution neural network for transfer learning of sentiment analysis in Indonesian tweets
AU - Jaya, Oki Saputra
AU - Murfi, Hendri
AU - Nurrohmah, Siti
N1 - Funding Information:
This work was supported by Universitas Indonesia under PITTA 2018 grant. Any opinions, findings, and conclusions or recommendations are the authors' and do not necessarily reflect those of the sponsor.
Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/7/20
Y1 - 2018/7/20
N2 - Sentiment analysis is an activity to classify public opinion about entities in textual data into positive or negative. One of the automatic methods for sentiment analysis is convolution neural network (CNN). CNN consists of many layers with many parameters that can be adjusted as needed to form a specific architecture. CNN works well in similar domains; however, it gives less accurate in different domains. Therefore, we consider transfer learning which transfers knowledge from a source domain to different but related target domains. In this paper, we examine parameter sensitivity and accuracy of CNN for transfer learning of sentiment analysis in Indonesian tweets. Our simulation shows that the parameters are very sensitive and incremental learning significantly increases the accuracy of transfer learning of the CNN model.
AB - Sentiment analysis is an activity to classify public opinion about entities in textual data into positive or negative. One of the automatic methods for sentiment analysis is convolution neural network (CNN). CNN consists of many layers with many parameters that can be adjusted as needed to form a specific architecture. CNN works well in similar domains; however, it gives less accurate in different domains. Therefore, we consider transfer learning which transfers knowledge from a source domain to different but related target domains. In this paper, we examine parameter sensitivity and accuracy of CNN for transfer learning of sentiment analysis in Indonesian tweets. Our simulation shows that the parameters are very sensitive and incremental learning significantly increases the accuracy of transfer learning of the CNN model.
KW - Convolution neural network
KW - Deep learning
KW - Incremental learning
KW - Sentiment analysis
KW - Transfer learning
KW - Twitter
UR - http://www.scopus.com/inward/record.url?scp=85055714271&partnerID=8YFLogxK
U2 - 10.1145/3239283.3239299
DO - 10.1145/3239283.3239299
M3 - Conference contribution
AN - SCOPUS:85055714271
T3 - ACM International Conference Proceeding Series
SP - 18
EP - 22
BT - Proceedings of the 2018 International Conference on Data Science and Information Technology, DSIT 2018
PB - Association for Computing Machinery
T2 - 2018 International Conference on Data Science and Information Technology, DSIT 2018
Y2 - 20 July 2018 through 22 July 2018
ER -