Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Indonesian Journal of Artificial Intelligence and Data Mining

Consumer Opinion Extraction Using Text Mining for Product Recommendations On E-Commerce Erlina Halim; Ronsen Purba; Andri Andri
Indonesian Journal of Artificial Intelligence and Data Mining Vol 4, No 1 (2021): March 2021
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v4i1.10834

Abstract

This study aims to evaluate consumer opinions in text form on e-commerce to determine the accuracy of ratings given by consumers with opinions using text mining with the lexicon approach. The research data was obtained online using a crawling technique using the API provided by Shopee. The conditions of diverse opinions and use of non-standard words are challenges in processing opinions. Opinion must be processed normalization and repairs using dictionary of words before going to extract using lexicon approach. Dictionary of words contain opinions with weights that are worth 1 to 5 for positive opinions and are worth -1 to -5 for negative opinions. For each opinion will be classified using the maximum ratio of the weight of positive opinion compared to the weight of negative opinion. The classification of opinion produced is positive, negative or neutral. Opinion classification is then compared with the rating classification to work out the extent of accuracy. The comparison produces an accuracy of 80.34% by completing an opinion dictionary.
Stock Price Prediction Using XCEEMDAN-Bidirectional LSTM -Spline Kelvin Chen; Ronsen Purba; Arwin Halim
Indonesian Journal of Artificial Intelligence and Data Mining Vol 5, No 1 (2022): March 2022
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v5i1.14424

Abstract

Bidirectional Long Short Term Memory (Bidirectional LSTM) is a machine learning technique with the ability to capture data context by traversing backward data to forward data and vice versa. However, the characteristics of stock data with large fluctuations, high dimensions and non-linearity become a challenge in obtaining high stock price prediction accuracy values. The purpose of this study is to provide a solution to the problem of stock data characteristics with large fluctuations, high dimensions and non-linearity by combining the Complete Ensemble Empirical Mode Decomposition With Adaptive Noise method for exogenous features (XCEEMDAN), Bidirectional Long Short Term Memory (LSTM), and Splines. The predicted data will go through normalization and preprocessing using XCEEMDAN then the XCEEMDAN decomposition results are divided into high and low frequency signals. The bidirectional LSTM handles high frequency signals and the Spline model handles low frequency signals. The test is carried out by comparing the proposed XCEEMDAN-Bidirectional LSTM-Spline model with the XCEEMDAN-LSTM-Spline model using the same parameters and changing the noise seed randomly 50 times. The test results show that the proposed model has the smallest RMSE average value of0.787213833 while model which is compared only has the smallest RMSE average value of 0.807393567.