Affiliation:
1. Information Systems, Universitas Amikom Purwokerto, Purwokerto, Jawa Tengah, Indonesia
2. Department of Commerce Chulalongkorn Business School, Chulalongkorn University, Bangkok, Thailand
Abstract
The primary objective of this research is to create a multi-output classification model for sentiment analysis through the combination of 10 algorithms: BernoulliNB, Decision Tree, K-nearest neighbor, Logistic Regression, LinearSVC, Bagging, Stacking, Random Forest, AdaBoost, and ExtraTrees. In doing so, we aim to identify the optimal algorithm performance and role within the model. The data utilized in this study is derived from customer reviews of cryptocurrencies in Indonesia. Our results indicate that LinearSVC and Stacking exhibit a high accuracy (90%) compared to the other eight algorithms. The resulting multi-output model demonstrates an average accuracy of 88%, which can be considered satisfactory. This research endeavors to innovate in adaptive sentiment analysis classification by developing a multi-output model that utilizes a combination of 10 classification algorithms.
Reference33 articles.
1. Sentiment analysis algorithms: evaluation performance of the Arabic and English language;Abo,2018
2. Classification of tweets causing deadlocks in Jakarta streets with the help of algorithm C4.5;Aini;Journal of Applied Data Sciences,2021
3. Comparison of three time series forecasting methods on linear regression, exponential smoothing and weighted moving average;Ajiono;IJIIS: International Journal of Informatics and Information Systems,2023
4. A knowledge behavioral and intelligence management in fostering entrepreneurship for modern industries;Alfazzi;International Journal for Applied Information Management,2022
5. Sentiment analysis of GO-JEK services quality using Multi-Label Classification;Amalia;Journal of Physics: Conference Series,2021