Claim Missing Document
Check
Articles

ANALISIS SENTIMEN PADA MEDIA SOSIAL X TERHADAP IMPLEMENTASI KURIKULUM MERDEKA MENGGUNAKAN METODE FASTTEXT DAN LONG SHORT-TERM MEMORY (LSTM) Pangestu, Arif Fajar; Rahmat, Basuki; Sihananto, Andreas Nugroho
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 4 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i4.5665

Abstract

Perubahan kurikulum adalah keharusan untuk mengikuti perkembangan zaman dan memastikan standar pendidikan terpenuhi. Namun, perubahan ini sering kali menyebabkan kebingungan di kalangan pendidik dan orang tua, yang mengganggu proses pendidikan. Kurikulum Merdeka, yang diperkenalkan sebagai inovasi penting dalam pendidikan Indonesia, menawarkan kerangka kerja yang lebih baik dan sesuai dengan kebutuhan. Meskipun demikian, dengan meningkatnya jumlah peserta didik, tantangan yang dihadapi oleh sistem pendidikan Indonesia juga bertambah. Penelitian ini bertujuan untuk menganalisis opini yang muncul di media sosial X tentang implementasi Kurikulum Merdeka, menggunakan metode word embedding FastText dan model klasifikasi Long Short-Term Memory. Dua dataset uji coba digunakan dalam penelitian ini, yang pertama berisi 7.500 entri dan yang kedua 3.000 entri. Penelitian ini juga menguji delapan skenario yang berbeda, dengan kombinasi metode ekstraksi fitur Continuous Bag of Words dan Skip-Gram, serta variasi pemisahan data 80:20 dan 85:15. Hasilnya menunjukkan tingkat akurasi yang tinggi di semua skenario, di atas 85%. Temuan ini mengungkap dominasi sentimen negatif dalam setiap kategori yang diamati selama implementasi Kurikulum Merdeka, menunjukkan adanya beberapa tantangan atau hambatan dalam penerimaan dan penerapan kurikulum tersebut di berbagai lingkungan pendidikan
History Learning Game of the Three-Day Battle Surabaya with Branching Narrative Himawan, Rantau; Putra, Chrystia Aji; Sihananto, Andreas Nugroho
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3346

Abstract

This study presents the development of an educational history game about the Three-Day Battle in Surabaya, designed using a branching narrative approach to enhance students’ engagement and historical understanding. Traditional history learning in Indonesia often relies on memorization and lacks interactive media, leading to low student motivation. To address this issue, the game integrates a decision-based narrative structure that allows players to explore consequences, experience alternative paths, and engage with historical events through meaningful choices. The game was developed using the Unity Engine with iterative refinement involving playtesting and feedback-based adjustments to dialogue flow, minigame mechanics, and visual presentation. The evaluation involved 15 participants and employed the GUESS-18 instrument. The results indicate strong user reception, with high scores in Narrative Understanding and Game Engagement, while Playability and Aesthetics received moderate ratings, highlighting areas for visual and interaction improvements. Despite the short testing duration, the game demonstrated potential to support historical learning by increasing immersion and reinforcing students’ understanding of key events and cause–effect relationships during the Surabaya conflict. This study contributes to the field of educational game development by demonstrating the pedagogical value of branching narratives and providing a practical model that can be adapted to other historical topics in future research.
Pengembangan Game Edukasi RPG Petualangan 2D tentang Peristiwa Lautan Api Bandung Menggunakan Alur Cerita Naratif Bercabang Sankalla, Sabda; Putra, Chrystia Aji; Sihananto, Andreas Nugroho
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3402

Abstract

This study evaluates the effectiveness of a 2D educational adventure RPG integrating branching narratives and a Numberlink-based puzzle to enhance students’ understanding of the historical Bandung Lautan Api event. Addressing the persistent issue of low engagement in history classrooms, the research investigates whether interactive storytelling and embedded logic-puzzle tasks can strengthen learning outcomes and user experience. Using a design-based research approach, the game was tested with 23 junior high school students through a pre-test/post-test design and the Game User Experience Satisfaction Scale (GUESS-18). The results show a substantial increase in historical knowledge, with post-test scores significantly higher than pre-test scores, indicating strong knowledge acquisition following gameplay. GUESS-18 responses also reveal consistently positive user experiences, with high ratings for narrative quality, educational value, visual and audio aesthetics, and overall enjoyment. Students reported that branching choices improved immersion and reflective thinking, while the Numberlink puzzle supported active reasoning during missions. These findings demonstrate that the integration of interactive narrative structures and logic-based puzzles can effectively support both cognitive and affective dimensions of history learning. Overall, the study confirms the potential of game-based learning to enhance comprehension, motivation, and engagement, providing evidence that well-designed educational games can significantly improve learning performance and serve as a valuable supplement to conventional history instruction.
A Branching Narrative 2D Action RPG Game to Enhance Learning About the Ambarawa Battle Nandaru, Laudy Nurdibya; Putra, Chrystia Aji; Sihananto, Andreas Nugroho
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3420

Abstract

This study develops a historical educational game titled Pertempuran Ambarawa to address the persistent challenge of low student engagement and limited contextual understanding in history classrooms, where learning is often dominated by memorization-based instruction. To provide a more interactive and reflective learning experience, the game integrates a branching narrative structure, 2D action RPG mechanics, and stealth–strategy minigames within the Interactive Digital Narrative (IDN) framework. This approach is intended to enhance learners’ historical reasoning by situating them in decision-based scenarios that mirror the complexities of the Ambarawa Battle. The game was implemented in Unity with 2D pixel-art aesthetics and evaluated through a pre-test–post-test design involving 25 junior high school students. Results show a significant improvement in historical comprehension, with mean scores increasing from 59.2 to 79.2 and the Wilcoxon Signed-Rank test yielding p = 0.00077 (p < 0.05). User experience was assessed using the GUESS-18 instrument, achieving an overall rating of 4.29 (Very Good), with the Education and Branching Narrative dimensions receiving the highest scores. These findings indicate that narrative interactivity and contextualized gameplay meaningfully contribute to learning effectiveness. Overall, the study demonstrates that combining branching narratives with RPG-based exploration provides a compelling alternative learning medium, offering both pedagogical value and strong user acceptance in history education.
Hyperparameter Optimization of Hybrid LSTM-GRU using Genetic Algorithm for Stock Price Prediction Lumangkun, Mordekhai Gerin; Swari, Made Hanindia Prami; Sihananto, Andreas Nugroho
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3656

Abstract

Predicting stock prices in the banking sector, particularly for high-capitalisation stocks such as Bank Rakyat Indonesia (BBRI), remains challenging amid market volatility. While Hybrid LSTM-GRU models have demonstrated capability in capturing temporal dependencies in time-series data, prior studies have predominantly focused on manual tuning or optimization of single recurrent architectures, with limited application of Genetic Algorithms for optimizing hybrid recurrent networks in emerging stock markets (R1). This research aims to address this gap by implementing an evolutionary optimization framework using a Genetic Algorithm (GA) to automatically tune the hyperparameters of a Hybrid LSTM-GRU model for enhanced stock price forecasting accuracy. Historical BBRI data from November 2020 to June 2025 were preprocessed through normalization and transformed into supervised time-series sequences before being divided into training, validation, and testing sets. The GA was configured with a population size of 20, 80 generations, and a crossover rate of 0.8 to search for optimal learning rates, batch sizes, and hidden units. The optimized configuration identified 64 units for LSTM and GRU layers, a learning rate of 0.002, and a batch size of 16. The resulting model achieved an RMSE of 82.11 and an MAPE of 1.51%, representing a 20% error reduction compared to baseline hybrid models and outperforming benchmark approaches reported in prior studies (R1). Achieving a 1.51% MAPE indicates reliability for financial forecasting, supporting risk-sensitive investment decision-making (A). Overall, this study demonstrates that evolutionary hyperparameter optimization enhances hybrid deep learning architectures.
Co-Authors Abdul Rezha Efrat Najaf Abdurrahman, Nizar Achmad Junaidi Aditya Primayudha Aditya Rizqi Ardhana Afifudin, Muhammad Afriani, Regita Agung Mustika Rizki, Agung Mustika Agussalim Agussalim Agussalim Agussalim Agussalim, Agussalim Alif Wisam Desanta Fitrianto Alifah, Nurul Aini Amalia, Nadhia Rizqy Amri Muhaimin Anggraini PS Anggraini Puspita Sari Ani Dijah, Rahajoe Ar Romandhon, Mitzaqon Gholizhan Ardiansyah, Muhammad Dafa Arif Widiasan Subagio Basuki Rahmat Masdi Siduppa Bisma Putra Sulung Christianty, Theressa Marry Dwi Arman Prasetya Edi Sugiyanto Edi Sugiyanto Eristya Maya Safitri Fakhruddin, Fikri Farkhan Fauzi, Zaky Ahmad Fetty Tri Anggraeny Gusti Ahmad Fanshuri Alfarisy, Gusti Ahmad Fanshuri Henni Endah Wahanani Himawan, Rantau Izzatul Fithriyah Kartini Kartini Kartini Lesmana, Benedictus Rafael Lumangkun, Mordekhai Gerin M Shochibul Burhan, M Shochibul M. Arif Mardhavi M. Shochibul Burhan Made Hanindia Prami Swari Mardhavi, Arif Marselina, Anif Fitria Dewi Maulana Fauzan Maulana, Hendra Maulana, Yoga Mohammad, Farrel Adel Muhammad Afifudin Muhammad Dafa Ardiansyah Muhammad Muharrom Al Haromainy Naila, Amelia Maslaqun Nandaru, Laudy Nurdibya Nurhaliza, Risma Nurlaili, Afina Lina Octaviani, Vincentia Indri Pangestu, Arif Fajar Parlika, Rizky Pradana, Ilham Akbar Prami, Made Hanindia Putra, Chrystia Aji Putra, Gredy Christian Hendrawan Putra, Raditya Lungguk Satya Ramadhan, Dimas Dharu Rasjid, Azka Avicenna Ratna Yulistiani Retno Mumpuni Reza, Reno Alfa Safitri, Erista Maya Sankalla, Sabda Santosa, Mochammad Kevin Saputra, Dewa Raka Krisna Saputri, Asih Sebrina, Aida Fitriya Shahab, Muhammad Syaugi Suryandari, Sabrina Heryanti Taufiqurrahman, Rahmadany Fahreza Tirana Noor Fatyanosa, Tirana Noor Trianingsih, Arini Trimono, Trimono Wayan Firdaus Mahmudy Wiwik Handayani Yisti Vita Via Yudistira, Mochammad Ervinda Yulianto, Rusman