Dyah Sulistyowati Rahayu

Dyah Sulistyowati Rahayu

Auto-generated profile, based on publicly available information

Dyah Sulistyowati Rahayu

Universitas Pancasila

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2020
Verified
Conference Paper
Closed access
DRDyah Sulistyowati Rahayu
Dyah Sulistyowati Rahayu
HSHeru Suhartanto
Heru Suhartanto
Predict financial distress is an important thing for investor's need to decide whether should put the capital or not. The earning's performance is one of the sign of the distress. Case based reasoning is implementing the highest level of data similarity in its concept. The algorithm should be supported by huge data. This is in line with the Indonesia Stock Exchange's data that has not been maximally utilized. This CBR algorithm can be used to assess the financial company performance in order to make the right investment decision. The ability of this algorithm to do the prediction is showed by the accuracy result of 82%. This research also confirmed that the complete CBR system improves all of the evaluation scoring.

30 April 2026 in Jurnal Informatika: Jurnal Pengembangan IT
Verified
Journal Article
Open access
PDF file
DRDyah Sulistyowati Rahayu
Dyah Sulistyowati Rahayu
IPIman Paryudi
Iman Paryudi
EDErin Divayaning
Erin Divayaning
AZAfni Puspita Zahra
Afni Puspita Zahra
ADArsya Yan Duribta
Arsya Yan Duribta
– Imbalanced data remains a major challenge in sentiment analysis, where the dominance of positive reviews often leads to biased classification results and weak recognition of minority classes. This study aims to address the imbalance problem by applying Large Language Models (LLM) to generate synthetic negative reviews and comparing the results with the traditional SMOTE method. The research process begins with data collection through web scraping, followed by preprocessing using standard text cleaning techniques such as tokenization, stopword removal, and stemming. Augmentation is then performed with LLM to produce additional negative samples, while SMOTE is applied as a baseline method. The classification task is conducted using Support Vector Machine (SVM) with TF-IDF representation, and model performance is evaluated using accuracy, precision, recall, and F1-score. The findings show that LLM augmentation produces synthetic data highly similar to the original distribution, as confirmed by Kolmogorov-Smirnov and Wasserstein Distance tests. Furthermore, the SVM model trained with LLM-augmented data achieved higher accuracy and balanced performance compared to SMOTE, particularly in handling minority classes. In conclusion, the use of LLM provides a more effective and natural approach for text data balancing in sentiment analysis, offering significant improvement in classification quality with accuracy of 99.41%, while using SMOTE get accuracy of 98.12%.Â