Claim Missing Document
Check
Articles

Found 3 Documents
Search

Analisis Sentimen dari Aplikasi Shopee Indonesia Menggunakan Metode Recurrent Neural Network Herni Utami
Indonesian Journal of Applied Statistics Vol 5, No 1 (2022)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijas.v5i1.56825

Abstract

Sentiment analysis on unbalanced data will cause classification errors where the classification results tend to be in the majority class. Therefore, it is necessary to handle unbalanced data. In this study, a combination of synthetic minority oversampling technique (SMOTE) and Tomek link methods will be used to handle unbalanced data. In this study, we use the Recurrent Neural Network (RNN) method to analyze the sentiment of Shopee application users based on review data. Shopee Indonesia application review data shows that around 80% of Shopee application users have positive sentiments and 20% have negative sentiments, which means the data is not balance. In this study, preprocessing process with combination of synthetic minority oversampling technique (SMOTE) and Tomek link method used to handle the condition. The performance of the result is quite good, namely 80% accuracy, 84.1% precision, 92.5% sensitivity, 30% specificity, and 88.1% F1-score. It is better than performance of sentiment analysis that without preprocessing to handle imbalanced data.Keywords: sentiment analysis; imbalanced data; Tomek link; SMOTE; RNN
SSA-based hybrid forecasting models and applications Winita Sulandari; Subanar Subanar; Suhartono Suhartono; Herni Utami; Muhammad Hisyam Lee; Paulo Canas Rodrigues
Bulletin of Electrical Engineering and Informatics Vol 9, No 5: October 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (587.132 KB) | DOI: 10.11591/eei.v9i5.1950

Abstract

This study attempted to combine SSA (Singular Spectrum Analysis) with other methods to improve the performance of forecasting model for time series with a complex pattern. This work discussed two modifications of TLSAR (Two-Level Seasonal Autoregressive) modeling by considering the SSA decomposition results, namely TLSNN (Two-Level Seasonal Neural Network) and TLCSNN (Two-Level Complex Seasonal Neural Network). TLSAR consisted of a linear trend, harmonic, and autoregressive component. In contrast, the two proposed hybrid approaches consisted of flexible trend function, harmonic, and neural networks. Trend and harmonic function were considered as the deterministic part identified based on SSA decomposition. Meanwhile, NN was intended to handle the nonlinearity relationship in the stochastic part. These two SSA-based hybrid models were contemplated to be more flexible than TLSAR and more applicable to the series with an intricate pattern. The experimental studies to the monthly accidental deaths in USA and daily electricity load Jawa-Bali showed that the proposed SSA-based hybrid model reduced RMSE for the testing data from that obtained by TLSAR model up to 95%.
Forecasting electricity load demand using hybrid exponential smoothing-artificial neural network model Winita Sulandari; Subanar Subanar; Suhartono Suhartono; Herni Utami
International Journal of Advances in Intelligent Informatics Vol 2, No 3 (2016): November 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v2i3.69

Abstract

Short-term electricity load demand forecast is a vital requirements for power systems. This research considers the combination of exponential smoothing for double seasonal patterns and neural network model. The linear version of Holt-Winter method is extended to accommodate a second seasonal component. In this work, the Fourier with time varying coefficient is presented as a means of seasonal extraction. The methodological contribution of this paper is to demonstrate how these methods can be adapted to model the time series data with multiple seasonal pattern, correlated non stationary error and nonlinearity components together. The proposed hybrid model is started by implementing exponential smoothing state space model to obtain the level, trend, seasonal and irregular components and then use them as inputs of neural network. Forecasts of future values are then can be obtained by using the hybrid model. The forecast performance was characterized by root mean square error and mean absolute percentage error. The proposed hybrid model is applied to two real load series that are energy consumption in Bawen substation and in Java-Bali area. Comparing with other existing models, results show that the proposed hybrid model generate the most accurate forecast