Garuda - Garba Rujukan Digital

Analisis Sentimen Ulasan iPhone di Amazon Menggunakan Model Deep Learning BERT Berbasis Transformer Arif Fitra Setyawan; Amelia Devi Putri Ariyanto; Fari Katul Fikriah; Rozaq Isnaini Nugraha
Elkom: Jurnal Elektronika dan Komputer Vol. 17 No. 2 (2024): Desember : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v17i2.2150

This study aims to analyze the sentiment of iPhone product reviews fromAmazon using the BERT (Bidirectional Encoder Representations from Transformers) model to classify reviews as either positive or negative. The dataset, sourced from Kaggle, includes text reviews and star ratings, where high ratings indicate positive sentiment and low ratings indicate negative sentiment. After text preprocessing steps, including data cleaning, tokenization, and sentiment labeling, the BERT model was fine-tuned for sentiment classification, with the data split into training, validation, and test sets. Evaluation results demonstrate that the BERT model achieves a high classification accuracy, with an accuracy rate of 93.9% and a balanced F1 score between precision and recall. Confusion matrix evaluation also indicates that the model consistently identifies both positive and negative sentiments. This study shows that Transformer-based models like BERT are highly effective in understanding customer opinions in e-commerce, with broad application potential for data-driven decision-making in marketing strategies and product development.

Impact of Statistical and Semantic Features Extraction for Emotion Detection on Indonesian Short Text Sentences Ariyanto, Amelia Devi Putri; Fikriah, Fari Katul; Setyawan, Arif Fitra
CommIT (Communication and Information Technology) Journal Vol. 19 No. 1 (2025): CommIT Journal (in press)
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v19i1.11680

The ability to detect emotions in short texts is crucial because interpreting emotions on platforms like Twitter can offer insight into social trends and responses to specific events. Additionally, examining emotions in product reviews assists companies in comprehending customer sentiment, allowing them to improve the quality of their products and services. Most research on Indonesian language emotion detection utilizes statistical feature extraction, with limited discussion on the impact of both statistical and semantic feature extraction. Thus, the research aims to detect emotions in short texts equipped with an analysis of the impact of statistical and semantic features. Analysis of the impact of statistical and semantic features on short texts is necessary to identify the most effective approaches, improve detection accuracy, and ensure that the developed systems can better handle the variety and complexity of informal language. The data used are a public dataset originating from Twitter texts and product review texts in e-commerce. The research utilizes statistical features such as Term Frequency Inverse Document Frequency (TF-IDF) and semantic features such as Bidirectional Encoder Representations from Transformers (BERT). The evaluation results show that using semantic features significantly improves the performance of emotion detection in short texts by 13–24%. It is higher than using statistical features. Deep Learning (DL) algorithms based on neural networks have also been proven to outperform Machine Learning (ML) algorithms in detecting emotions in short text. The experimental results and outlines show the potential directions for future development.

Boosting Performance Klasifikasi kNN Customer Loyalty dengan Chi-Square dan Information Gain Mutiarachim, Atika; Fikriah, Fari Katul; Ansor, Basirudin; Ramdani, Aditya Putra
Jurnal Transformatika Vol. 22 No. 2 (2025): January 2025
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/6wgy1097

Understanding customer purchasing behavior is essential for predicting customer loyalty, which directly impacts a company's long-term success. This research aims to determine the effect of chi-square and information gain feature selection in optimizing customer loyalty classification performance, compared to pure kNN. Using a public customer purchasing behavior dataset from Kaggle, containing 10,000 data, 12 attributes with loyalty_status as the label (Gold, Regular, Silver). Evaluating performance by accuracy, kappa, classification error, recall, precision, and RMSE. The highest accuracy 91.99% was obtained by kNN k=3 with information gain, kappa 0.844, precision 95.44%, recall 86.30%, with the lowest classification error 8.01% and the second lowest RMSE 0.245, after kNN k=3 with chi-square. Results show that feature selection has a positive impact on classification, increasing accuracy and reducing errors, with the combination of the kNN k=3 method and information gain proving successful in obtaining high accuracy in classifying customer loyalty.

Penerapan Teknologi Artificial Intelligence Sebagai Media Inovatif dalam Mendukung Proses Pembelajaran dan Kreativitas Siswa Paket C di PKBM Bangkit Kota Semarang Fikriah, Fari Katul; Ariyanto, Amelia Devi Putri
Jurnal Pengabdian Masyarakat Nusantara (JPMN) Vol. 5 No. 1 (2025): Februari - Juli 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jpmn.v5i1.4595

The rapid development of information technology requires educational institutions, including Community Learning Activity Centers (PKBM), to innovate in improving the quality of learning and fostering student creativity. PKBM Bangkit Kota Semarang as a non-formal educational institution still faces obstacles in the form of low learning motivation and limited technology-based learning media. This community service activity aims to design and implement Artificial Intelligence (AI) technology as an innovative media to support the learning process and encourage the creativity of Package C students. The implementation method includes identifying partner needs, designing and developing AI media, training and mentoring, implementing in class, and monitoring and evaluation. The results of the community service show that AI-based learning media has succeeded in increasing learning participation, facilitating access to materials, encouraging independent learning, and receiving positive responses from tutors and students. These findings demonstrate that the application of AI in PKBM has the potential to be an innovative solution for strengthening the quality of non-formal education in the digital era.

Penerapan Teknologi Artificial Intelligence Sebagai Media Inovatif dalam Mendukung Proses Pembelajaran dan Kreativitas Siswa Paket C di PKBM Bangkit Kota Semarang Fikriah, Fari Katul; Ariyanto, Amelia Devi Putri
Jurnal Pengabdian Masyarakat Nusantara (JPMN) Vol. 5 No. 1 (2025): Februari - Juli 2025
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jpmn.v5i1.4595

The rapid development of information technology requires educational institutions, including Community Learning Activity Centers (PKBM), to innovate in improving the quality of learning and fostering student creativity. PKBM Bangkit Kota Semarang as a non-formal educational institution still faces obstacles in the form of low learning motivation and limited technology-based learning media. This community service activity aims to design and implement Artificial Intelligence (AI) technology as an innovative media to support the learning process and encourage the creativity of Package C students. The implementation method includes identifying partner needs, designing and developing AI media, training and mentoring, implementing in class, and monitoring and evaluation. The results of the community service show that AI-based learning media has succeeded in increasing learning participation, facilitating access to materials, encouraging independent learning, and receiving positive responses from tutors and students. These findings demonstrate that the application of AI in PKBM has the potential to be an innovative solution for strengthening the quality of non-formal education in the digital era.

Emotion Detection Using Contextual Embeddings for Indonesian Product Review Texts on E-commerce Platform Ariyanto, Amelia Devi Putri; Fari Katul Fikriah; Arif Fitra Setyawan
Pixel :Jurnal Ilmiah Komputer Grafis Vol. 17 No. 1 (2024): Pixel :Jurnal Ilmiah Komputer Grafis dan Ilmu Komputer
Publisher : UNIVERSITAS STEKOM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/pixel.v17i1.2010

The advancement of e-commerce has changed the way people shop. However, there is a mismatch between the actual quality of a product and the seller’s description. Product reviews are an important source of information for making purchasing decisions. However, processing large numbers of reviews manually is difficult. This research aims to detect emotions in Indonesian language product review texts using contextual embeddings. The public dataset used was PRDECT-ID, which comprises five emotion labels. The methods used include data preprocessing, feature extraction using contextual embeddings such as Bidirectional Encoder Representations from Transformers (BERT), and classification using Decision Tree, Naïve Bayes, and k-Nearest Neighbors (KNN). Among the compared models, the KNN model demonstrated the highest improvement, achieving a 15.09% enhancement over the decision tree results. This research provides insights into the effectiveness of contextual embeddings in detecting emotions in Indonesian language product review texts.

SIDEMA (Sistem Informasi Desa Menawan) untuk Peningkatan Pelayanan Masyarakat dalam Upaya Mewujudkan Digital Village di Desa Menawan Kabupaten Grobogan Fikriah, Fari Katul; Nugaraha, Rozaq Isnaini; Verawati, Liesta
Jurnal Pengabdian UNDIKMA Vol. 5 No. 4 (2024): November
Publisher : LPPM Universitas Pendidikan Mandalika (UNDIKMA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33394/jpu.v5i4.13302

This community service activity aims to implement the Menawan Village Information System (SIDEMA) to facilitate data management and services to the community and the dissemination of village information digitally. The implementation of this program includes an initial survey of technology needs, system implementation, implementation of socialization and training for residents and the Menawan Village apparatus, Grobogan Regency. The results of the community service show that the implementation of SIDEMA is able to increase service efficiency and facilitate residents' access to public information. SIDEMA is expected to function optimally in supporting the Digital Village vision. The evaluation carried out showed that the community was satisfied with the community service activities that had been carried out. Further development and replication of this system to other villages is a strategic step in realizing technology-based villages in Indonesia.

Instance Selection dengan Naïve Bayes pada Klasifikasi Kanker Serviks Fikriah, Fari Katul
Jurnal Komtika (Komputasi dan Informatika) Vol 5 No 2 (2021)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/komtika.v5i2.6041

There are several deadly disease for woman, one of which is servical cancer. The growth and development of the disease is very slow, so that treatment if know form the beginning will facilitate the healing process, but conversely unknown cancers from the beginning will become dangereous and deadly disease due to relatively difficult healing. Biopsy action is one way to detect the presence of cancer. In the previous study, classification of cervical cancer had the bighest accuracy value of 97,515% using the decision tree method of several feature selection technique. for this reason, this research will use the decision tree or tree C4.5 classification method, logistic function and zeroR which were previously carried out processing with instance selection with Naïve Bayes by reducing the elimination of missing values with the aim of increasing the level of accuracy better than previous studies. C4.5 classification in this study has the most maximum results compared to other classification methods with an accuracy value of 99,69%.

Naïve Bayes untuk Klasifikasi Penyakit Daun Bawang Merah Berdasarkan Ekstraksi Fitur Gray Level Cooccurrence Matrix (GLCM) Fikriah, Fari Katul; Burhanis Sulthan, M; Mujahidah, Nailatul; Khoirur Roziqin, Moh.
Jurnal Komtika (Komputasi dan Informatika) Vol 6 No 2 (2022)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/komtika.v6i2.7925

Bawang merah merupakan salah satu produk pertanian yang menjadi bagian komoditas rempah-rempah yang biasa digunakan sebagai bahan masakan. Dalam pengelolaan bawang merah ini tentu terdapat beberapa kendala, pengamatan pada kondisi penanaman bawang merah bisa dilihat dari perubahan yang terjadi pada daunnya. Terdapat beberapa sebab yang menjadikan panen bawang merah menjadi menurun walaupun semakin banyak petani yang menanam bawang merah tersebut. Diantara penyebab gagalnya panen yang dialami petani bawang merah adalah adanya penyakit yang menyerang pada daunnya. Penyakit pada daun bawang merah juga beraneka macam serta memiliki beberapa gejala yang berbeda-beda. Klasifikasi pada penyakit daun bawang merah memberikan langkah untuk ketahananan tanaman yang berkelanjutan. Penyakit daun bawang merah harus diklasifikasikan berdasarkan jenisnya agar bisa mendapatkan penanganan yang tepat. Penelitian ini bertujuan untuk mengklasifikasikan penyakit daun bawang merah berdasarkan ekstraksi fitur Gray Level Co-occurrence Matrix (GLCM) yang didapat dari citra daun bawang merah dengan mengambil empat fitur yaitu energy, contrast, correlation serta homogeneity, sedangkan metode algoritma yang dipakai untuk klasifikasi penyakit daun bawang tersebut adalah Naïve Bayes dengan akurasi sebesar 62%.

Monitoring dan Klasifikasi Kualitas Air Kolam Ikan Gurami Berbasis Internet of Things Menggunakan Metode Naive Bayes Kristiyanto, Arip; Fikriah, Fari Katul; Inkiriwang, Rully; Andriansah, Zulfi
Jurnal Komtika (Komputasi dan Informatika) Vol 7 No 2 (2023)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/komtika.v7i2.10200

Ministry of Marine Affairs and Fisheries (KKP) noted that Indonesia produced 56,539 tons of gourami fish in the second quarter of 2022 High market demand and economical selling prices encourage farmers to cultivate gourami fish. In cultivating gourami fish there are several obstacles, for example, disease caused by poor water quality. Water quality is the main parameter in the success of gourami fish farming. This research aims to develop a water quality monitoring system based on the Internet of Things. The system prototype uses a temperature sensor (DS18B20), Ph sensor (dfrobot SEN0161), turbidity sensor (dfrobot SEN0189), flowmeter, and ultrasonic sensor (JSN-SR04) as input. The Arduino Mega R3 microcontroller is the processor and the Oled module (SSD1306) is the output. Thingboard is a cloud server that functions as sensor data monitoring. Temperature sensor testing results (DS18B20) average error 0.48%, Ph(dfrobot SEN0161) sensor testing average error 0.64%, ultrasonic sensor testing (JSN-SR04) average error 7.83%, testing Turbidity sensors can measure the level of water turbidity. Next, the water quality parameter data is processed using the Naïve Bayes algorithm method for classifying the water quality of gourami ponds. The results of this classification obtained an accuracy of 99.94% a Kappa Statistics value of 0.9989 and a Mean Absolute Error of 0.0003

Title

Found 29 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 29 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 29 Documents
Search