TY - GEN
T1 - A Robustly Optimized BERT using Random Oversampling for Analyzing Imbalanced Stock News Sentiment Data
AU - Permataning Tyas, Salsabila Mazya
AU - Sarno, Riyanarto
AU - Haryono, Agus Tri
AU - Rossa Sungkono, Kelly
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Stock news is one of the information sources that can used to monitor stock prices. The information from stock news usually contains positive and negative sentiments that can affect stock prices. Therefore, sentiment analysis is needed to process the sentiment of stock news. The stock news dataset is taken from Kaggle. From these data, there is an imbalanced class between positive and negative sentiment. This research proposed a method to solve the imbalance dataset with random oversampling which worked by randomly replicating several minority classes. This research presents several scenarios of pre-processing text with different stages, intending to get high accuracy. The classification method used in this paper is a robustly optimized Bidirectional Transformer Encoder Representation (RoBERTa). Besides that, this paper also compared with baseline of Machine Learning (ML) such as Multinomial Naïve Bayes, Bernoulli Naïve Bayes, Support Vector Machine, Random Forest Classifier, Logistic Regression and used two different text representation such as TF-IDF and Word2Vec. The best result in this research is obtained using RoBERTa method with the fourth scenario of pre-processing text, in which the stage of pre-processing in this scenario only removing hashtag, without removing punctuation, removing the number, converting number, stop word removal, and lemmatization. The performance result is 0.85 precision, 0,84 recall, 0,84 F1-score, and 86% for accuracy result.
AB - Stock news is one of the information sources that can used to monitor stock prices. The information from stock news usually contains positive and negative sentiments that can affect stock prices. Therefore, sentiment analysis is needed to process the sentiment of stock news. The stock news dataset is taken from Kaggle. From these data, there is an imbalanced class between positive and negative sentiment. This research proposed a method to solve the imbalance dataset with random oversampling which worked by randomly replicating several minority classes. This research presents several scenarios of pre-processing text with different stages, intending to get high accuracy. The classification method used in this paper is a robustly optimized Bidirectional Transformer Encoder Representation (RoBERTa). Besides that, this paper also compared with baseline of Machine Learning (ML) such as Multinomial Naïve Bayes, Bernoulli Naïve Bayes, Support Vector Machine, Random Forest Classifier, Logistic Regression and used two different text representation such as TF-IDF and Word2Vec. The best result in this research is obtained using RoBERTa method with the fourth scenario of pre-processing text, in which the stage of pre-processing in this scenario only removing hashtag, without removing punctuation, removing the number, converting number, stop word removal, and lemmatization. The performance result is 0.85 precision, 0,84 recall, 0,84 F1-score, and 86% for accuracy result.
KW - pre-processing text
KW - random oversampling
KW - robustly optimized BERT
KW - sentiment analysis
KW - stock news
UR - http://www.scopus.com/inward/record.url?scp=85163075040&partnerID=8YFLogxK
U2 - 10.1109/ICCoSITE57641.2023.10127725
DO - 10.1109/ICCoSITE57641.2023.10127725
M3 - Conference contribution
AN - SCOPUS:85163075040
T3 - ICCoSITE 2023 - International Conference on Computer Science, Information Technology and Engineering: Digital Transformation Strategy in Facing the VUCA and TUNA Era
SP - 897
EP - 902
BT - ICCoSITE 2023 - International Conference on Computer Science, Information Technology and Engineering
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Conference on Computer Science, Information Technology and Engineering, ICCoSITE 2023
Y2 - 16 February 2023
ER -