Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : IPSIKOM

ANALISIS SENTIMEN MASYARAKAT TERHADAP PINJAMAN ONLINE DI APLIKASI X MENGGUNAKAN LONG SHORT-TERM MEMORY Hafizh Maalik Falah; Castaka Agus Sugianto
IPSIKOM Vol. 13 No. 2 (2025): Jurnal Ipsikom
Publisher : LPPM UNIVERSITAS INSAN PEMBANGUNAN INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58217/ipsikom.v13i2.429

Abstract

The development of online loans in Indonesia has led to various public opinions spread across social media, one of which is the X platform. This research aims to analyze public sentiment towards online loans using the Long Short-Term Memory (LSTM) method. The data used consists of 702 Indonesian tweets collected through a crawling process with Tweet Harvest. Of these, 480 tweets were classified as positive sentiment and 222 as negative. The research process includes preprocessing, manual labeling, model training, and evaluation stages. The model was built using Sequential architecture from Keras, consisting of embedding layer, LSTM layer 128 units, 30% dropout, and output layer with softmax activation function. The model was trained using 562 tweets as training data and 140 tweets as validation data with a ratio of 80:20, for 10 epochs and batch size 64. The final evaluation using the entire dataset resulted in 92.59% accuracy, with 79.06% precision, 79.43% recall, and 79.14% F1-score. These results show that LSTM is able to classify sentiment stably and effectively, and has strong potential in sentiment analysis on short text data such as tweets.
DETEKSI KESEGARAN IKAN BANDENG DENGAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) Rudi Riansyah; Castaka Agus Sugianto
IPSIKOM Vol. 13 No. 2 (2025): Jurnal Ipsikom
Publisher : LPPM UNIVERSITAS INSAN PEMBANGUNAN INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58217/ipsikom.v13i2.442

Abstract

Fish freshness is a key indicator in ensuring food quality and safety, especially in milkfish (Chanos chanos) which is widely consumed in Indonesia. Manual freshness assessment is subjective and requires special skills, so an accurate automated approach is needed. This study aims to develop a digital image-based milkfish freshness classification application using the Convolutional Neural Network (CNN) method with a transfer learning approach. The dataset used consists of 445 milkfish images in two classes: fresh and not fresh, with an augmentation process to enrich the visual variety. Two models were compared: Model A (baseline) and Model B (enhancement with Dropout and fine-tuning). The evaluation results show that Model A has 33% accuracy, 50% precision, and 50% recall, In contrast, Model B has 67% accuracy, 50% precision, and 100% recall, showing more stable prediction in Streamlit-based applications. These findings suggest that the integration of CNN and transfer learning can be effectively applied to support the digitization of fish-based food product quality. Further development is suggested through the addition of training data, multi-class classification, and integration to mobile or IoT devices.