Articles
<![CDATA[SGCF: Inductive Movie Recommendation System with Strongly Connected Neighborhood Sampling ]]>
<![CDATA[Jatmiko Budi Baskoro]]>;
<![CDATA[Evi Yulianti]]>
<![CDATA[ Jurnal Ilmu Komputer dan Informasi Vol. 15 No. 1 (2022): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio ]]>
Publisher : <![CDATA[Faculty of Computer Science - Universitas Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21609/jiki.v15i1.1066
<![CDATA[User and item embeddings are key resources for the development of recommender systems. Recent works has exploited connectivity between users and items in graphs to incorporate the preferences of local neighborhoods into embeddings. Information inferred from graph connections is very useful, especially when interaction between user and item is sparse. In this paper, we propose graphSAGE Collaborative Filtering (SGCF), an inductive graph-based recommendation system with local sampling weight. We conducted an experiment to investigate recommendation performance for SGCF by comparing its performance with baseline and several SGCF variants in Movielens dataset, which are commonly used as recommendation system benchmark data. Our experiment shows that weighted SGCF perform 0.5% higher than benchmark in NDCG@5 and NDCG@10, and 0.8% in NDCG@100. Weighted SGCF perform 0.79% higher than benchmark in recall@5, 0.4% increase for recall@10 and 1.85% increase for recall@100. All the improvements are statistically significant with p-value < 0.05.]]>
<![CDATA[VALIDITAS LKS PENGAMATAN BERDASARKAN PENDEKATAN SAINTIFIK PADA SUB POKOK BAHASAN ANGIOSPERMAE ]]>
<![CDATA[EVI YULIANTI]]>
<![CDATA[ Berkala Ilmiah Pendidikan Biologi (BioEdu) Vol 3 No 3 (2014) ]]>
Publisher : <![CDATA[Program Studi Pendidikan Biologi, FMIPA, Universitas Negeri Surabaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Kurangnya keterlibatan siswa secara langsung dalam kegiatan pengamatan dan cakupan materi yang luas menjadikan siswa sering menemui kesulitan dalam memahami konsep Angiospermae. Diperlukan kegiatan pembelajaran yang dapat melatih siswa bersikap ilmiah, kreatif, dan mandiri untuk memudahkan siswa memahami konsep. Pendekatan saintifik merupakan pendekatan yang menerapkan kaidah ilmiah dalam pembelajaran meliputi kegiatan mengamati, menanya, mencoba, menalar, dan mengkomunikasikan. Penelitian ini bertujuan untuk mengetahui kelayakan LKS ditinjau dari aspek validitas. Penelitian ini merupakan penelitian pengembangan dengan mengacu pada model pengembangan Research & Development (R&D). Hasil penelitian menunjukkan bahwa LKS yang dikembangkan layak berdasarkan hasil validasi (91,25%) dengan interpretasi sangat layak. Kata Kunci: Lembar Kegiatan Siswa, Pendekatan Saintifik, Angiospermae]]>
<![CDATA[Legal Protection Of Victims In The Crime Of Rapes ]]>
<![CDATA[Evi Yulianti]]>;
<![CDATA[Achmad Sulchan]]>
<![CDATA[ Law Development Journal Vol 3, No 2 (2021): June 2021 ]]>
Publisher : <![CDATA[Universitas Islam Sultan Agung ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (644.283 KB)
|
DOI: 10.30659/ldj.3.2.353-361
<![CDATA[The purpose of this study is to identify and analyze the legal protection of victims in the crime of rape, and to identify and analyze the obstacles and solutions to the legal protection of victims in the crime of rape. This study uses a normative juridical approach, which in this case relates to the legal protection of victims in the crime of rape with descriptive analytical research specifications. The data used are primary and secondary data which will be analyzed qualitatively. The research problems were analyzed using law enforcement theory, legal certainty and Islamic justice theory. The results of the study concluded that the protection of victims of the crime of rape in addition to experiencing physical suffering also experienced psychological suffering which took a long time to recover. Considering that the suffering experienced by the victims of the crime of rape is not light and it takes a long time to recover, the law enforcement officers are obliged to provide protection for the victims of the crime of rape. The obstacles that arise in the legal protection of the rights of victims in the process of resolving criminal cases: a) The criminals themselves, where the perpetrators of the crime are very good at committing crimes so that they are not caught or not caught; b) The attitude of the community, where the attitude of the community is indifferent in dealing with crimes that occur in their environment, so that people are less sensitive in dealing with crimes that occur; c) The compensation given by the perpetrator to the victim is not in accordance with what the victim expects because of the economic limitations of the perpetrator of the crime; d) For immaterial losses in criminal cases it cannot be done. The solution to the legal protection of victims in the crime of rape is the rehabilitation of victims of the crime of rape.]]>
<![CDATA[Analisis struktur morfologi membran kitosan/PEO dan kitosan/PEG4000 ]]>
<![CDATA[Kartika Sari]]>;
<![CDATA[Sunardi Sunardi]]>;
<![CDATA[Agung Bambang Setio Utomo]]>;
<![CDATA[Edi Suharyadi]]>;
<![CDATA[Evvy Kartini]]>;
<![CDATA[Evi Yulianti]]>
<![CDATA[ Jurnal Teras Fisika: Teori, Modeling, dan Aplikasi Fisika Vol 3 No 1 (2020): Jurnal Teras Fisika: Teori, Modeling, dan Aplikasi Fisika ]]>
Publisher : <![CDATA[Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.20884/1.jtf.2020.3.1.2756
<![CDATA[Pembuatan dan pengujian membran kitosan/PEO dan kitosan/PEG4000 dilakukan bertujuan untuk membandingkan struktur morfologi dan gugus fungsi yang dihasilkan dari membran kitosan/PEO dan kitosan/PEG4000. Pembuatan membran Kitosan/PEO dan kitosan/PEG4000 dilakukan dengan metode solution casting. Karakterisasi dilakukan menggunakan FTIR (Fourier Transform Infra Red) dan SEM (Scanning Electron Microscopy). Hasil FTIR membran kitosan, kitosan/PEO dan kitosan/PEG4000 menunjukkan adanya interaksi gugus fungsi –OH dan C-H di dalam membran kitosan/PEO dan kitosan/PEG4000. Bilangan gelomgang 1500 – 945 cm-1 terbentuk ikatan bending antara gugus fungsi C-C dan –NH3. Hasil SEM menunjukkan terbentuk agglomerasi dengan bertambahnya PEO dan PEG4000 pada larutan. Agglomerasi terjadi homogen di permukaan membran menunjukkan adanya pengaruh penambahan PEO dan PEG4000 pada pembentukan membran sehingga menghasilkan ikatan antar atom yang semakin renggang/tidak stabil. Hasil membran kitosan/PEO dan kitosan/PEG4000 dapat digunakan sebagai polimer elektrolit padat.]]>
<![CDATA[Sintesis dan Karakterisasi Membran Kitosan/LiOH sebagai Elektrolit Padat Baterai Sekunder ]]>
<![CDATA[Sunardi Sunardi]]>;
<![CDATA[Aris Haryadi]]>;
<![CDATA[Wihantoro Wihantoro]]>;
<![CDATA[Evi Yulianti]]>
<![CDATA[ Jurnal Teras Fisika: Teori, Modeling, dan Aplikasi Fisika Vol 2 No 1 (2019): Jurnal Teras Fisika: Teori, Modeling, dan Aplikasi Fisika ]]>
Publisher : <![CDATA[Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (361.229 KB)
|
DOI: 10.20884/1.jtf.2019.2.1.1334
<![CDATA[Sintesis dan karakterisasi membran Kitosan/LiOH dilakukan bertujuan untuk menentukan pengaruh PVA/LiOH terhadap mikrostruktur membran elektrolit padat baterai sekunder. Sintesi membran Kitosan/LiOH dilakukan dengan metode casting dengan variasi konsentrasi w/w LiOH. Karakterisasi dilakukan menggunakan FTIR (Fourier Transform Infra Red) dan SEM (Scanning Electron Microscopy). Hasil FTIR membran kitosan/LiOH menunjukkan adanya interaksi antara kitosan/LiOH. Pada panjang gelombang 3500 nm terbentuk gugus fungsi –OH baru dan pada 1500 – 945 nm terbentuk ikatan bending antara gugus fungsi –OH dengan –NH3. Hasil SEM menunjukkan terbentuk agglomerasi dengan bertambahnya konsentrasi LiOH pada larutan. Terjadi distribusi partikel homogen di permukaan membran. Hal ini menunjukkan bahwa adanya pengaruh penambahan LiOH pada pembentukan membran yang menghasilkan ikatan antar atom yang semakin renggang/tidak stabil dan bahan yang semakin konduktif.]]>
<![CDATA[Determining subject headings of documents using information retrieval models ]]>
<![CDATA[Evi Yulianti]]>;
<![CDATA[Laksmita Rahadianti]]>
<![CDATA[ Indonesian Journal of Electrical Engineering and Computer Science Vol 23, No 2: August 2021 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v23.i2.pp1049-1058
<![CDATA[Subject heading is a controlled vocabulary that describes the topic of adocument, which is important to find and organize library resources. Assigning appropriate subject headings to a document, however, is a time-consuming process. We therefore conduct a novel study on the effectiveness of information retrieval models, i.e.,language model (LM) andvector spacemodel (VSM), to automatically generate a ranked list of relevant subject headings, with the aim to give a recommendation for librarians to determine the subject headings effectively and efficiently. Our results show that there are a high number of our queries (up to 61%) that have relevant subject headings in the ten top-ranked recommendations and on average, the first relevant subject heading is found at the early position (3rd rank). This indicates that document retrieval methods can help the subject heading assignment process. LM and VSM are shown to have comparable performance, except when the search unit is title, VSM is superior to LM by8-22%. Our further analysis exhibits three faculty pairs that are potential to have research collaboration as their students’ thesis often have overlap subject headings: i) economy and business-social and political sciences, ii) nursing-public health and iii) medicine-public health.]]>
<![CDATA[Multi-label text classification of Indonesian customer reviews using bidirectional encoder representations from transformers language model ]]>
<![CDATA[Nuzulul Khairu Nissa]]>;
<![CDATA[Evi Yulianti]]>
<![CDATA[ International Journal of Electrical and Computer Engineering (IJECE) Vol 13, No 5: October 2023 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijece.v13i5.pp5641-5652
<![CDATA[Customer review is a critical resource to support the decision-making process in various industries. To understand how customers perceived each aspect of the product, we can first identify all aspects discussed in the customer reviews by performing multi-label text classification. In this work, we want to know the effectiveness of our two proposed strategies using bidirectional encoder representations from transformers (BERT) language model that was pre-trained on the Indonesian language, referred to as IndoBERT, to perform multi-label text classification. First, IndoBERT is used as feature representation to be combined with convolutional neural network-extreme gradient boosting (CNN-XGBoost). Second, IndoBERT is used both as the feature representation as well as the classifier to directly solve the classification task. Additional analysis is performed to compare our results with those using multilingual BERT model. According to our experimental results, our first model using IndoBERT as feature representation shows significant performance over some baselines. Our second model using IndoBERT as both feature representation and classifier can significantly enhance the effectiveness of our first model. In summary, our proposed models can improve the effectiveness of the baseline using Word2Vec-CNN-XGBoost by 19.19% and 6.17%, in terms of accuracy and F-1 score, respectively.]]>
<![CDATA[Enhanced TextRank using weighted word embedding for text summarization ]]>
<![CDATA[Evi Yulianti]]>;
<![CDATA[Nicholas Pangestu]]>;
<![CDATA[Meganingrum Arista Jiwanggi]]>
<![CDATA[ International Journal of Electrical and Computer Engineering (IJECE) Vol 13, No 5: October 2023 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijece.v13i5.pp5472-5482
<![CDATA[The length of a news article may influence people’s interest to read the article. In this case, text summarization can help to create a shorter representative version of an article to reduce people’s read time. This paper proposes to use weighted word embedding based on Word2Vec, FastText, and bidirectional encoder representations from transformers (BERT) models to enhance the TextRank summarization algorithm. The use of weighted word embedding is aimed to create better sentence representation, in order to produce more accurate summaries. The results show that using (unweighted) word embedding significantly improves the performance of the TextRank algorithm, with the best performance gained by the summarization system using BERT word embedding. When each word embedding is weighed using term frequency-inverse document frequency (TF-IDF), the performance for all systems using unweighted word embedding further significantly improve, with the biggest improvement achieved by the systems using Word2Vec (with 6.80% to 12.92% increase) and FastText (with 7.04% to 12.78% increase). Overall, our systems using weighted word embedding can outperform the TextRank method by up to 17.33% in ROUGE-1 and 30.01% in ROUGE-2. This demonstrates the effectiveness of weighted word embedding in the TextRank algorithm for text summarization.]]>
<![CDATA[Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using Bert Language Models ]]>
<![CDATA[Lenggo Geni]]>;
<![CDATA[Evi Yulianti]]>;
<![CDATA[Dana Indra Sensuse]]>
<![CDATA[ Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol 9, No 3 (2023): September ]]>
Publisher : <![CDATA[Universitas Ahmad Dahlan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26555/jiteki.v9i3.26490
<![CDATA[General election is one of the crucial moments for a democratic country, e.g., Indonesia. Good election preparation can increase people's participation in the general election. In this study, we conduct a sentiment analysis of Indonesian public opinion on the upcoming 2024 election using Twitter data and IndoBERT model. This study is aimed at helping the government and related institutions to understand public perception. Therefore, they could obtain valuable insights to better prepare for elections, including evaluating the election policies, developing campaign strategies, increasing voter engagement, addressing issues and conflicts, and increasing transparency and public trust. The main contribution of this study is threefold: (i) the application of state-of-the-art transformer-based model IndoBERT for sentiment analysis on political domain; (ii) the empirical evaluation of IndoBERT model against machine learning and lexicon-based models; and (iii) the new dataset creation for sentiment analysis in political domain. Our Twitter data shows that Indonesian public mostly reacts neutrally (83.7%) towards the upcoming 2024 election. Then, the experimental results demonstrate that IndoBERT large-p1 is the best-performing model that achieves an accuracy of 83.5%. It improves our baseline systems by 48.5% and 46.49% for TextBlob, 2.5% and 14.49% for Multinomial Naïve Bayes, and 3.5% and 13.49% for Support Vector Machine in terms of accuracy and F-1 score, respectively.]]>
<![CDATA[WORKSHOP PENDAMPINGAN PENGGUNAAN APLIKASI E-VOTING UNTUK PEMILIHAN OSIS ]]>
<![CDATA[Imelda Saluza]]>;
<![CDATA[Evi Yulianti]]>;
<![CDATA[Lastri Widya Astuti]]>;
<![CDATA[Dhamayanti Dhamayanti]]>
<![CDATA[ RESWARA: Jurnal Pengabdian Kepada Masyarakat Vol 5, No 1 (2024) ]]>
Publisher : <![CDATA[Universitas Dharmawangsa ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.46576/rjpkm.v5i1.4047
<![CDATA[Salah satu kegiatan non akademik di sekolah kegiatan Organisasi Siswa Intra Sekolah (OSIS). SMP Negeri 4 Banyuasin 1 Sumatera Selatan selaku mitra tim PKM menyampaikan permasalahan pada kegiatan non akademik yang dihadapi berdasarkan hasil observasi dan wawancara. Dalam proses pelaksanaan kegiatan OSIS, ditemui beberapa hambatan antara lain belum adanya pemanfataan teknologi dalam kegiatan non akademik mitra padahal mitra telah memiliki kesiapan teknologi serta sumber daya untuk menggunakannya, kegiatan non akademik yang masih menganggu proses pembelajaran serta tidak efektif dalam kegiatannya. Berdasarkan permasalahan yang dihadapi mitra, Pengabdian Kepada Masyarakat (PKM) Universitas Indo Global Mandiri (IGM) dan mitra menyepakati untuk mengadakan kegiatan PKM penggunaan aplikasi e-voting guna mendukung bidang non akademik. Tujuan kegiatan ini adalah untuk memberikan bimbingan teknis yang menjelaskan bagaimana sistem e-voting bekerja, termasuk bagaimana suara dihitung dan hasil diumumkan. Hal ini dapat meningkatkan transparansi dan kepercayaan para pemilih terhadap integritas pemilihan. Kegiatan ini dapat memberikan wawasan tentang bagaimana pemilihan berlangsung yang memungkinkan panitia pemilihan OSIS untuk memantau, mengevaluasi proses serta membuat perbaikan di masa akan datang serta membantu kebutuhan dalam pelaksanaan pembaruan struktur ogansisasi mitra dalam menunjang pelaksanaan kegiatan non akademik. Kegiatan dilakukan dengan menggunakan metode difusi IPTEKS dan workshop. Workshop dilaksanakan tanggal 19 April 2023 untuk melakukan evaluasi terhadap kegiatan tim memberikan kuesioner kepada peserta untuk menilai kegiatan yang telah dilakukan. Berdasarkan analisis hasil evaluasi kegiatan PKM mitra menilai pelaksanaan workshop memberikan kemudahan dalam pemilihan dibanding acara tradisional, proses perhitungan lebih cepat sehingga efektif digunakan, perhitungan, keamanan dan kerahasiaan terjamin. Hasil penilaian dari peserta dapat disimpulkan bahwa peserta menyetujui untuk menggunakan aplikasi e-voting untuk pemilihan OSIS dengan persentase indeks penilaian di atas 75%.]]>
