Article Per Year (5 Year)
p-Index From 2020 - 2025
0.882
P-Index
This Author published in this journals
All Journal Jurnal Pilar Nusa Mandiri Empowerment Society Journal of Informatics Development
Urrochman, Maysas Yafi
Unknown Affiliation
Humanities Computer Science & IT Social Sciences

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Sentiment Analysis of Ijen Crater Reviews using Decision Tree Classification and Oversampling Optimization Hizham, Fadhel Akhmad; Asyari, Hasyim; Urrochman, Maysas Yafi
Journal of Informatics Development Vol. 3 No. 1 (2024): Oktober 2024
Publisher : Institut Teknologi dan Bisnis Widya Gama Lumajang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30741/jid.v3i1.1399

Abstract

Sentiment analysis is a text mining technique that classifies content as positive, negative, or neutral polarity in each sentence or document. These lines or papers may be user reviews assessing the quality of a product or material supplied to them. The purpose of this study is to better understand the function of sentiment analysis in assessing evaluations of the Ijen Crater tourist destination based on Google Maps user comments. This study is conducted in four steps, beginning with data gathering in the form of Google Maps evaluations obtained by data scraping. Following data collection, text preparation includes case folding, tokenization, stopword elimination, and stemming. Following text preprocessing, the next stage is imbalaced data optimization, which involves modifying the minority class samples to be nearly equal to the majority class by randomly duplicating minority class samples. Then, each review is categorized according to sentiment using the Decision Tree (DT) method. Testing has done by comparing DT without optimization and DT with SMOTE-ENN and ADASYN optimization. The result shown DT with SMOTE-ENN optimization has the best accuracy improvement with 1.62%, from 96.94% to 98.56%.
PERFORMANCE COMPARISON OF RANDOM FOREST REGRESSION, SVR MODELS IN STOCK PRICE PREDICTION Urrochman, Maysas Yafi; Asy'ari, Hasyim; Hizham, Fadhel Akhmad
Jurnal Pilar Nusa Mandiri Vol. 21 No. 1 (2025): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v21i1.6072

Abstract

The stock market is characterized by high volatility and complexity, making it an intriguing and challenging subject for researchers and practitioners. This study aims to predict stock prices by comparing the performance of two machine learning models: Random Forest Regression and Support Vector Regression (SVR). These models were selected for their ability to handle complex data and high volatility. The dataset used in this study consists of BNI stock data over the last five years (2019–2024), comprising a total of 1,211 data points. Testing was conducted using a cross-validation approach, and model performance was evaluated based on several metrics, including MSE, R², RMSE, MAPE, MAE, and Score. The results indicate that Random Forest Regression outperforms SVR. The model achieved an MAE of 17.766, an RMSE of 22.376, and an R² of 0.997. These findings suggest that Random Forest Regression is more effective in predicting stock prices, particularly in unstable market conditions. This study recommends Random Forest Regression as a reliable model for stock price prediction, with potential applications in other stock markets with similar characteristics.
AnalysisSentimentAlun-Alun LumajangReviewusingSupportVector Machine Urrochman, Maysas Yafi
Journal of Informatics Development Vol. 3 No. 2 (2025): April 2025
Publisher : Institut Teknologi dan Bisnis Widya Gama Lumajang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30741/jid.v3i2.1555

Abstract

Alun-Alun Lumajangis one of room the public that becomes center activity community and tourists . Perception public to place Thiscan measured through analysis sentiment to reviews available on digital platforms such as Google Maps. Research This aiming For classifysentiment review the use Support Vector Machine (SVM) method , one of the effective machine learning algorithms Fortask classification text . Data used in the form of review collected text fromGoogle Maps, then through pre-processing data such as cleaning text , tokenization , and deletion stopword . Sentiment label determined manually to be three categories : positive, negative , and neutral . Next , the data is extracted use TF-IDF technique before classified using SVM. Research results showthat SVM algorithm is capable of classify sentiment with level high accuracy , making it proper method For analysis opinion public based on text . Findings This expected can give input for government area in increase quality services and management room public in Lumajang.
Appropriate Technology Innovation “Biopharmaka Grinder” as a Means of Optimizing the Economy of the Senduro Community – Lumajang Ermawati, Emmy; Istichomah, Istichomah; Urrochman, Maysas Yafi
IMPOWERMENT SOCIETY Vol 8 No 1 (2025): February
Publisher : Institut Teknologi dan Bisnis Widya Gama Lumajang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30741/eps.v8i1.1392

Abstract

Lumajang Regency, Senduro District, East Java is famous as a center for the production of spices and herbs. Due to its abundant natural potential, various biopharmaceutical plants have been developed and are now major players in the local agricultural industry. The area is rich in natural resources, including vast agricultural lands and a climate that supports the cultivation of many medicinal plants. However, the challenge often faced by farmers is the lack of efficient processing equipment, which hinders the realization of the full potential of these biopharmaceutical components. Appropriate technological innovation The tool known as the “Biopharmaceutical Grinder” is intended to maximize the grinding of several biopharmaceutical raw materials, including spices, herbal plants, and other natural components.  Biopharmaceutical Grinder can increase the output and market value of local goods by creating an instrument that is easy to use and friendly to rural communities. The creation and distribution of the Biopharmaceutical Grinder is expected to enhance Senduro's position as a center for biopharmaceutical processing in East Java and make it a model for other regions that want to utilize their natural resources in an environmentally responsible manner.
Aspect-Based Sentiment Analysis of Tumpak Sewu Waterfall Tourist Reviews Using the Naive Bayes Classifier (NBC) Method Urrochman, Maysas Yafi; Asy’ari, Hasyim; Ro’uf, Abdur
Journal of Informatics Development Vol. 4 No. 1 (2025): Oktober 2025
Publisher : Institut Teknologi dan Bisnis Widya Gama Lumajang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30741/jid.v4i1.1758

Abstract

With the increasing popularity of Tumpak Sewu Waterfall, the volume of visitor reviews on Google Maps continues to grow. These reviews contain valuable insights into tourists’ experiences; however, conducting an in-depth manual analysis is inefficient. This study aims to perform aspect-based sentiment analysis on visitor reviews of Tumpak Sewu Waterfall using the Naive Bayes Classifier (NBC) method. This approach enables the classification of sentiments positive, negative, and neutral based on specific aspects such as facilities, accessibility, and natural scenery. Review data were collected from online platforms and processed through stages of text preprocessing and feature extraction before being trained using the NBC model. The results show that the model effectively classifies review sentiments with a high level of accuracy and provides detailed insights into which aspects most influence visitor satisfaction. These findings not only demonstrate the effectiveness of the Naive Bayes Classifier in aspect-based sentiment analysis tasks but also offer data-driven strategic recommendations for tourism managers to enhance service quality and improve visitor experience in the future.
Co-Authors Asy'ari, Hasyim Asy’ari, Hasyim Emmy Ermawati Hasyim Asyari Hizham, Fadhel Akhmad Istichomah Istichomah, Istichomah Ro’uf, Abdur