Article Per Year (5 Year)
p-Index From 2021 - 2026
0.702
P-Index
This Author published in this journals
All Journal Brilliance: Research of Artificial Intelligence
Ani Anisyah
Universitas Pendidikan Indonesia, Indonesia
Decision Sciences, Operations Research & Management Mathematics Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
A Dental Chatbot Based on IndoBERT with Next Sentence Prediction and Intent Classification Nadhief Athallah Isya; Rasim Rasim; Ani Anisyah
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6620

Abstract

Low public awareness regarding the importance of dental health remains a significant issue in Indonesia. This situation is exacerbated by limited access to consultation services that are easy, fast, affordable, and available at any time. As a result, many dental diseases go undetected at an early stage. Additionally, the tendency to delay dental check-ups is often caused by time constraints and the distance to healthcare facilities, leading many people to avoid consulting with dentists. To address this problem, this research developed a dental health chatbot based on Natural Language Processing (NLP) using IndoBERT. The model was pretrained with the Masked Language Model (MLM) approach and fine-tuned using Next Sentence Prediction (NSP) and intent classification tasks. The dataset was compiled from Indonesian-language dental health articles, symptom–disease sentence pairs, and follow-up questions, all validated by certified dentists. The system was implemented as a web application using React JS for the frontend, Express JS and MySQL for the backend, and integrated with the NLP model through a Flask API. Evaluation results show that the chatbot can provide relevant dental health information, including lightweight consultations to assist in early symptom detection, answer follow-up questions, and generate digital medical records. Expert validation produced an average score of “Good” across the aspects of clarity, relevance, medical accuracy, and completeness, with Likert scale scores ranging from 3.53 to 3.67. This research is expected to contribute as an accessible 24-hour online dental health information service aimed at increasing public knowledge and awareness.
Development of an Academic Services Chatbot Based on Retrieval-Augmented Generation (RAG) Mohammad Labib Husain; Yudi Wibisono; Ani Anisyah
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6719

Abstract

Higher education institutions struggle to provide accurate and accessible academic information. Traditional chatbots are often limited in capability, while standard Large Language Models (LLMs) pose a significant risk of factual "hallucinations," rendering them unsuitable for official university use where trustworthiness is paramount. This study aims to increase the accessibility and effectiveness of academic services by developing a trustworthy chatbot. The primary objective is to implement the Retrieval-Augmented Generation framework to create a reliable AI assistant that is factually grounded in a verified, domain-specific knowledge base. A knowledge base was constructed from official FPMIPA UPI documents and structured using hierarchical chunking. The system employs a multi-stage RAG pipeline featuring query contextualization and reranking before generation with Gemini 2.5 Pro. Performance was evaluated using metrics from the RAGAS framework on a 100-question dataset categorized into factual, reasoning, and out-of-context queries. The evaluation revealed strong performance on factual queries, achieving a Faithfulness score of 0.9100. A significant performance decrease was observed for reasoning tasks, with Context Recall dropping to 0.5926. Crucially, the system successfully handled 81.25% of out-of-context questions by correctly refusing to answer, thereby effectively preventing hallucination. The RAG framework provides a viable and empirically-validated blueprint for creating a trustworthy conversational AI for higher education. The model proves to be an effective tool for factual information delivery and has strong potential to modernize how student support and academic services are delivered.
Stock Price Prediction Using the ETSFormer Model Case Study: PTBA Muhammad Azka Atqiya; Lala Septem Riza; Ani Anisyah
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6729

Abstract

The capital market in Indonesia is currently experiencing very rapid development. This growth is significantly evidenced by the increasing number of investors, especially from the millennial and Gen Z demographics. However, this growing investor base also faces a major challenge: high stock price volatility. These fluctuations are triggered by various factors, ranging from domestic economic policies and global geopolitical conditions to rapidly changing market sentiment. This research aims to build a stock price prediction model for PT Bukit Asam Tbk (PTBA) using the ETSFormer architecture, a modern Transformer-based method designed for time-series data. The historical stock price data used in this study covers a five-year period from 2020 to 2025. To ensure optimal model performance, the best model was identified using the Grid Search technique to find the most effective combination of hyperparameters. The results of this study determined that the best model was achieved with the hyperparameters model dimension = 16, batch size = 16, and a learning rate = 0.01, which yielded a validation loss of 0.0074. In the evaluation phase, this model demonstrated solid performance with a MAPE score of 3.28%, an MAE of 86.76, and an RMSE of 117.2. Although the resulting model is quite good at reading long-term trend directions, observations indicate limitations in capturing short-term price volatility. This implies that the model is more suitable for strategic trend analysis than for predicting daily fluctuations.
Non-Playable Characters Based On Large Language Models For Role Playing Games (RPG) Ade Mulyana; Yudi Wibisono; Ani Anisyah
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.6779

Abstract

Interactive dialogue is a central element in role-playing games (RPG), particularly those that emphasize storytelling and immersion. This study explores the development of a dynamic Non-Playable Character (NPC) system using a Large Language Model (LLM) to simulate responsive conversations in a fictional world. The objective of this research is to design an NPC dialogue system that can maintain contextual consistency with the game’s lore while adapting to player input dynamically. The method used is engineering-based development, involving prompt engineering and a Retrieval-Augmented Generation (RAG) approach to embed narrative context into the LLM prompts. The system is implemented in a 2D RPG titled Kage no Meiyaku: Shinobi no Michi, where players interact with multiple NPCs whose responses evolve based on both pre-defined lore and game progression. Evaluation is conducted using a Likert scale across four dialogue quality dimensions: coherence, emotional engagement, narrative relevance, and persona consistency. The results show that the system generates engaging and contextually accurate responses, with average scores ranging from 4.0 to 4.5. Some limitations are identified, such as occasional misspellings and generic responses in ambiguous inputs. However, the approach demonstrates strong potential for AI-assisted storytelling in games. This research contributes to expanding LLM applications in interactive fiction and opens future work toward feature-rich RPG elements such as transactional systems, branching narratives, and real-time battle interactions.
Co-Authors Ade Mulyana Lala Septem Riza Mohammad Labib Husain Muhammad Azka Atqiya Nadhief Athallah Isya Rasim Rasim Yudi Wibisono