Hasil Pencarian  ::  Simpan CSV :: Kembali

"This monograph presents key method to successfully manage the growing complexity of systems where conventional engineering and scientific methodologies and technologies based on learning and adaptability come to their limits and new ways are nowadays required. The transition from adaptable to evolvable and finally to self-evolvable systems is highlighted, self-properties such as self-organization, self-configuration, and self-repairing are introduced and challenges and limitations of the self-evolvable engineering systems are evaluated."

"Co-authored by ASTD President and CEO Tony Bingham, and long-time workplace educator and Fast Company business writer Marcia Conner, this book shows readers how social media can help trainers and workers increase their knowledge, innovate faster than their competitors, and enjoy themselves in a way that increases their commitment to their employer and to the customers they ultimately serve."

"Contents :- What social learning is not - Social learning technologies - Trends in social learning - Dealing with critics and objections - How to implement social learning - What's next - References & resources - Job aid "

"Ilmu Data adalah irisan dari matematika dan statistika, komputer, serta keahlian domain. Dalam beberapa tahun terakhir inovasi pada bidang ilmu data berkembang sangat pesat, seperti Artificial Intelligence (AI) yang telah banyak membantu kehidupan manusia. Deep Learning (DL) sebagai bagian dari AI merupakan pengembangan dari salah satu model machine learning yaitu neural network. Dengan banyaknya jumlah lapisan neural network, model deep learning mampu melakukan proses ekstrasi fitur dan klasifikasi dalam satu arsitektur. Model ini telah terbukti mengungguli teknik state-of-the-art machine learning di beberapa bidang seperti pengenalan pola, suara, citra, dan klasifikasi teks. Model deep learning telah melampaui pendekatan berbasis AI dalam berbagai tugas klasifikasi teks, termasuk analisis sentimen. Data teks dapat berasal dari berbagai sumber, seperti sumber dari media sosial. Analisis sentimen atau opinion mining merupakan salah satu studi komputasi yang menganalisis opini dan emosi yang diekspresikan pada teks. Pada penelitian ini analisis peforma machine learning dilakukan pada metode deep learning berbasis representasi data BERT dengan metode CNN dan LSTM serta metode hybrid deep learning CNN-LSTM dan LSTM-CNN. Implementasi model menggunakan data komentar youtube pada video politik dengan topik terkait Pilpres 2024, kemudian evaluasi peforma dilakukan menggunakan confusion metric berupa akurasi, presisi, dan recall.

---

Data Science is the intersection of mathematics and statistics, computing, and a domain of expertise. In recent years innovation in the field of data science has developed very rapidly, such as Artificial Intelligence (AI) which helped a lot in human life. Deep Learning (DL) as part of AI is the development of one of the machine learning models, namely neural network. With the large number of neural network layers, deep learning models are capable of performing feature extraction and classification processes in a single architecture. This model has proven to outperform state-of-the-art machine learning techniques in areas such as pattern recognition, speech, imagery, and text classification. Deep learning models have gone beyond AI-based approaches in a variety of text classification task, including sentiment analysis. Text data can come from various sources, such as source from social media. Sentiment analysis or opinion mining is a computational study that analyze opinions and emotions expressed in text. In this research, machine learning performance analysis is carried out on a deep learning method based on BERT data representation with the CNN and LSTM and hybrid deep learning CNN-LSTM and LSTM-CNN method. The implementation of the model uses YouTube commentary data on political videos related to the 2024 Indonesia presidential election, then performance analysis is carried out using confusion metrics in the form of accuracy, precision, and recall."

"ABSTRAKIndividu dengan tunagrahita memiliki kebutuhan yang berbeda terkait dengan pendidikan dan perkembangan seksual. Penelitian ini dilakukan untuk mengetahui efektivitas teori belajar sosial dengan strategi berupa cerita sosial dan contoh melalui video dalam meningkatkan keterampilan perawatan selama masa menstruasi pada subjek remaja perempuan dengan disabilitas intelektual ringan. Penguasaan keterampilan perawatan selama menstruasi diuji dengan tiga cara yaitu 1 menggunakan kuesioner menstruasi milik Klett dan Turan 2012 yang telah dimodifikasi; 2 menggunakan uji pemahaman; 3 menggunakan proses simulasi melalui dua tipe pembalut yang berbeda yaitu pembalut dengan sayap dan tanpa sayap yang berisi darah buatan terbuat dari tepung maizena dan pewarna makanan warna merah. Hasil menunjukkan bahwa program intervensi teori belajar sosial efektif meningkatkan keterampilan perawatan selama masa menstruasi pada subjek. Saran untuk selanjutnya ialah agar program ini dilaksanakan oleh pengasuh pada subjek selaku pihak yang sehari-hari berhubungan langsung dengan subjek.

---

ABSTRACTIndividuals with intellectual disabilities have different needs related to education and sexual development. This study was conducted to determine the effectiveness program based on social learning theory in the form of social stories and video modeling to improve skills on menstrual care in female adolescent with mild intellectual disabilities. Mastery skills on menstrual care tested in three ways 1 using a menstrual questionnaire belongs to Klett and Turan 2012 which has been modified 2 using a test comprehension and 3 the simulation process through two types of pads that the pads with wings and without wings that contain artificial blood is made from cornstarch and food coloring in red. The results showed that intervention programs effective to improve skills on menstrual care in subject. It is suggested to implement this program to the parents or caregiver, instead to the subject."

"Dalam peminjaman uang atau kredit, financial trustworthiness adalah suatu elemen penting dalam menentukan kepercayaan dan resiko finansial seseorang. Institusi pemilik produk kredit menggunakan pemeringkatan kredit untuk menilai financial trustworthiness sebelum memberikan kredit. Masalah muncul ketika seseorang yang tidak memiliki riwayat keuangan tidak bisa dikenali oleh sistem pemeringkatan kredit sehingga pengajuan kredit mereka beresiko tertolak. Di lain sisi, keberadaan smartphone diperkirakan akan menghubungkan sekitar 73% penduduk di negara-negara Asia di tahun 2025. Maka, smartphone dapat menjadi alat untuk mengakses perilaku seseorang. Setelah melibatkan seratus sembilan puluh delapan responden menjawab tiga puluh satu pertanyaan dalam survei perilaku penggunaan smartphone, diperoleh sebelas pertanyaan paling berpengaruh dengan 70.4% variansi. Survei baru yang dilakukan pada 714 orang menjawab sebelas pertanyaan yang digunakan untuk memodelkan financial trustworthiness. Dalam tesis ini, pemodelan financial trustworthiness memanfaatkan metode machine learning dalam dunia keuangan. Pemodelan dilakukan menggunakan bahasa pemrograman Python yang dikerjakan pada Jupyter Notebook, bagian dari software pengolah data Anaconda. Dilakukan pemisahan data menjadi training set dan testing set dengan pembagian 80:20 masing-masing. Kemudian beberapa algoritma diujikan untuk mengetahui performanya. Hasil penelitian menunjukan ke empat algoritma dinyatakan model yang baik dengan performa lebih dari 0,8. Logistic Regression menunjukan akurasi 0,874, presisi 0,90, recall 0,87. Sedangkan Decision Tree dengan akurasi 0,967, presisi 0,97, recall 0,97. Pada SVM menunjukan akurasi 0,825, presisi 0,83, recall 0,83. Sementara Naïve Bayes memiliki nilai presisi 1,00, akurasi 1,00, recall 1,00. Hal ini menjadikan algoritma Naïve Bayes memiliki performa paling baik dan sempurna.

---

In money lending or credit, financial trustworthiness is an important element in deciding the trust and financial risk of a person. Financial institution with credit product, uses credit rating measure for financial trustworthiness before giving the credit. Problem arises when people whith no financial history is unrecognized by the credit rating system, then their credit application is in the risk of being rejected. On the other side, prediction says that smartphone will connect approximately 73% of Asian countries citizen in 2025. Therefore, smartphone could become a device to access peoples behavior. We involved one hundred ninety eight respondents to answer thirty one questions on smartphone usage behavior. The survey generates eleven most influencial questions with 70.4% variance. Then, the new survey was conducted to 714 people who answers eleven questions used to model the financial trustworthiness. In this thesis, we present a financial trustworthiness model implementing machine learning method in financial world. In our proposed work, we use Python programming language which works in Jupyter Notebook, and the part of data processing software Anaconda. The next stage is data splitting into training set and testing set with partition of 80:20 each part. Subsequently, some algorithms were tested to compare the performance. The research result shows four algorithm stated as good model with performance more than 0.8. Logistic Regression shows accuracy of 0.874, precision of 0.90, recall of 0.87. While Decision Tree with accuracy of 0.967, precision of 0.97, recall of 0.97. In SVM display accuracy of 0.825, precision of 0.83, recall of 0.83. Meanwhile, Naïve Bayes has a precision of 1.00, accuracy of 1.00, recall of 1.00. This made Naïve Bayes algorithm as the best and perfect in performance."

"Penyebaran virus Covid-19 di Indonesia pada tahun 2020 berdampak pada bidang edukasi dimana diberlakukan kebijakan pembelajaran jarak jauh, baik untuk sekolah maupun kegiatan edukasi non-formal. Dikarenakan kondisi tersebut, portal pembelajaran daring di Indonesia semakin gencar mempromosikan layanannya pada media sosial yang dimiliki untuk mendapatkan pelanggan. Analisis deskriptif ini menganalisis unggahan media sosial oleh empat portal pembelajaran daring di Indonesia yang paling dikenal dan aktif dalam menggunakan media sosial, yang merupakan Ruangguru, Quipper School, Rumah Belajar, dan Kelas Pintar. Kerangka analisis yang digunakan untuk menganalisis unggahan media sosial portal pembelajaran daring dari tanggal 16 Maret hingga 16 April 2020 ini adalah tabel strategi konten pemasaran media sosial. Hasil dari analisis ini adalah unggahan media sosial oleh empat portal pembelajaran daring sesuai dengan strategi konten kreatif media sosial tersebut, dan Ruangguru merupakan portal pembelajaran daring di Indonesia yang paling aktif dalam menggunakan media sosial. 

---

The spread of Covid-19 in Indonesia in 2020 impacted the education system in the country where school from home regulations applies to formal and informal education activities. Due to these regulations, online learning platforms in Indonesia promoted more of their services through social media platforms they own. This descriptive analysis analyzes social media posts made by four online learning platforms in Indonesia that are most known and active on social media usage, which includes Ruangguru, Quipper School, Rumah Belajar, and Kelas Pintar. The analytical frame that is used to analyze the social media posts from March 16 through April 16, 2020 is the table of content strategies on social media marketing. The results of this analysis includes social media posts made by four online learning platforms are in line with the content strategies on social media marketing table, and the most active online learning platform on social media usage in Indonesia is Ruangguru."

"Adanya peristiwa selama tahapan penyelenggaraan pemilu 2024, menimbulkan berbedaan pandangan diantara para Ahli, akan potensi terciptanya persepsi buruktentang Pemilu 2024. Sehingga dibutuhkan pengukuran perbandingan sentimen untuk menindaklanjuti dan membuktikan pandangan tersebut. Di sisi lain media sosial hadir sebagai tempat yang memungkinkan penggunanya untuk mengeskpresikan opini yang dimiliki, termasuk opini tentang penyelenggaraan Pemilu. Besarnya adopsi media sosial di Indonesia, memungkinkannya digunakan sebagai sumber data dalam pengukuran perbandingan sentimen masyarakat terkait dengan Pemilu 2024. Namun dalam menganalisa data yang berasal dari media sosial membutuhkan sumber daya dan waktu yang tidak sedikit jika dilakukan secara manual, dikarenakan adanya karakterstik high velocity, high volume dan high variety yang dimiliki oleh data yang berasal dari media sosial. Text analytics dengan pendekatan machine learning telah banyak digunakan dan menjadi state-of-the-art cara yang mengatasi permasalahan tersebut. Penelitian ini mengkomparasikan algoritma deep learning dengan algoritma machine learning tradisional seperti SVM, random forest dan logistic regression, dalam upaya membangun model analisis sentimen yang dapat digunakan untuk mengukur perbandingan sentimen masyarakat terhadap Pemilu 2024. Teknik pemodelan topik Latent Dirichlet Allocation juga digunakan untuk mengidentifikasi topik pembicaraan yang tersembunyi di dalamnya. Hasil dari penelitian menunjukkan algoritma SVM dengan teknik vektorisasi TF-IDF unigram muncul sebagai algoritma dengan hasil kinerja prediksi terbaik dengan nilai f1-score 0.7890. Selain itu terdapat dinamika pergeseran dominasi sentimen mulai dari masa kampanye, masa tenang dan masa pemungutan sampai dengan masa rekapitulasi suara. Hasil penelitian ini diharapkan dapat memberikan informasi yang bernilai bagi para pemangku kepentingan seperti: Pengamat politik, Praktisi politik, Pemerintah dan Penyelenggara Pemilu.

---

The events occurring during the stages of the 2024 General Election have sparked differing opinions among experts regarding the potential for negative perceptions of the election. Consequently, there is a need to measure sentiment patterns to follow up on and substantiate these views. Meanwhile, social media serves as a platform that allows users to express their opinions, including those about the election. The widespread adoption of social media in Indonesia enables it to be used as a data source for measuring public sentiment patterns related to the 2024 General Election. Analyzing data from social media requires significant resources and time if done manually, due to the high velocity, high volume, and high variety characteristics of social media data. Text analytics with a machine learning approach has been extensively used and has become the state-of-the-art method for addressing these challenges. This study compares deep learning algorithms with traditional machine learning algorithms such as Support Vector Machine (SVM), Random Forest, and Logistic Regression in an effort to build a sentiment analysis model that can be used to measure public sentiment patterns toward the 2024 General Election. The Latent Dirichlet Allocation (LDA) topic modeling technique is also used to identify hidden discussion topics within the data. The results of the study indicate that the SVM algorithm with TF-IDF unigram vectorization technique emerged as the algorithm with the best predictive performance, achieving an f1-score of 0.7890. Meanwhile, the measurement of sentiment patterns showed dynamic shifts in sentiment from the campaign period, the quiet period, and the voting period up to the recapitulation period. The findings of this study are expected to provide valuable information for stakeholders such as political observers, political practitioners, the government, and election organizers."

"This book examines the deliberate deployment of what the author calls "hypermodulation", as a key strategy encoded into the contemporary media environment. This account challenges the various narratives that portray social media as a sinister space of synchronized attention, in which we are busily "clicking ourselves to death". This critical reflection on the unprecedented power of the Internet requires us to rethink the potential for infinite distraction that our latest technologies now allow."