Perkembangan teknologi saat ini tidak bisa lepas dengan dunia pendidikan. Berbicara tentang dunia pendidikan tidak lepas dengan peran siswa, mahasiswa, guru dan dosen. Untuk siswa dan mahasiswa mulai banyak keluhan dengan kurang menariknya pembelajaran yang mereka dapatan. Keluhan ini tentunya mengusik pada guru dan dosen sebagai pemberi materi. Untuk itu perlu adanya pendampingan kepada guru dan dosen dalam penyampaian materi pada siswa dan mahasiswa. Pada kegiatan pengabdian ini akan diadakan pendampingan guru dan dosen dalam pembuatan media pembelajaran yang merupakan salah satu bentuk pemberian materi yang dilaksanakan saat ini. Pada pendampingan ini diberikan materi tentang pemanfaatan Artificial Intelligent (AI) pada aplikasi Capcut dalam pembuatan video pembelajaran. Dalam pendampingan ini guru dikenalkan penggunaan aplikasi Capcut dalam pembuatan video pembelajaran. Setelah itu guru dan dosen diberikan cara pemanfaatan AI pada fitur aplikasi Capcut yang mana bisa memberikan efisiensi waktu dalam pengeditan, keramahan dan kemudahan dalam penggunaannya, menghasilkan video yang berkualitas, mempunyai fleksibilitas pemanfaatan yang dibutuhkan oleh siswa dan mahasiswa. Dengan adanya pemanfaatan tersebut, maka guru dan dosen lebih mudah dan kretif dalam pemanfaatan AI pada fitur aplikasi Capcut untuk membuat video pembelajaran. Dengan pendampingan ini, diharapkan siswa dan mahasiswa akan terpenuhi mendapatkan pengajaran yang menarik dan tidak membosankan.Kata kunci: Video pembelajaran, fitur, capcut

Breast cancer is the most prevalent cancer among women worldwide, requiring early and accurate diagnosis to reduce mortality. This study proposes a hybrid classification pipeline that integrates Hybrid Statistical Feature Selection (HSFS) with unsupervised LSTM-guided feature extraction for breast cancer detection using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. Initially, 20 features were selected using HSFS based on Mutual Information, Chi-square, and Pearson Correlation. To address class imbalance, the training set was balanced using the Synthetic Minority Over-sampling Technique (SMOTE). Subsequently, an LSTM encoder extracted non-linear latent features from the selected features. A fusion strategy was applied by concatenating the statistical and latent features, followed by re-selection of the top 30 features. The final classification was performed using a Support Vector Machine (SVM) with RBF kernel and evaluated using 5-fold cross-validation and a held-out test set. Experimental results showed that the proposed method achieved an average training accuracy of 98.13%, F1-score of 98.13%, and AUC-ROC of 99.55%. On the held-out test set, the model reached an accuracy of 99.30%, precision of 100%, and F1-score of 99.05%, with an AUC-ROC of 0.9973. The proposed pipeline demonstrates improved generalization and interpretability compared to existing methods such as LightGBM-PSO, DHH-GRU, and ensemble deep networks. These results highlight the effectiveness of combining statistical selection and LSTM-based latent feature encoding in a balanced classification framework.

Information technology has developed and provided progress such as the increasing use of computers and the internet in the world, especially in the world of education. Through computers and the internet, all information can be disseminated and can be used as learning materials for students. The development of information technology and the internet, not all information is disseminated positively. Some information is disseminated negatively such as fake news (hoaxes), radicalism, and hate speech. There needs to be skills in using the development of information technology. Digital literacy trains users not only to be proficient in using information technology but also to have the ability to think critically, creatively, and innovatively to produce digital competence. SMA At Thohiriyyah is one of the high schools in Semarang that focuses on understanding and improving the abilities of its students in digital literacy. Insight is needed for SMA At Thohiriyyah students in understanding the importance of digital literacy. Animation video training is one way to increase student creativity in digital literacy in creating learning videos. With this training, it is hoped that students can develop learning videos that can be used on social media such as YouTube

The extraordinary use of YouTube at this time indicates that developments in the world of technology are very rapid. But it must always be aware that technological developments also affect the psychological development of children. As is the case at the age of children - teenagers who sometimes cannot control. The development of the use of technology, information and communication in the digital world has had various impacts on our lives. As happened at SMA At Thohiriyyah Semarang, which has a middle to lower economic background and is located on the outskirts of East Semarang. At that high school, the students still don't understand the correct use of YouTube. They just watch content that is sometimes not useful. With these problems, they must be given assistance on how to use YouTube properly. For this reason, they must be made active in using YouTube by having an account and being able to create useful content for other people. Apart from that, they are expected to be able to entertain other people through the content they create

This research aims to improve the effectiveness of lung cancer classification performance using Support Vector Machines (SVM) with hyperparameter tuning. Using Radial Basis Function (RBF) kernels in SVM helps deal with non-linear problems. At the same time, hyperparameter tuning is done through Random Grid Search to find the best combination of parameters. Where the best parameter settings are C = 10, Gamma = 10, Probability = True. Test results show that the tuned SVM improves accuracy, precision, specificity, and F1 score significantly. However, there was a slight decrease in recall, namely 0.02. Even though recall is one of the most important measuring tools in disease classification, especially in imbalanced datasets, specificity also plays a vital role in avoiding misidentifying negative cases. Without hyperparameter tuning, the specificity results are so poor that considering both becomes very important. Overall, the best performance obtained by the proposed method is 0.99 for accuracy, 1.00 for precision, 0.98 for recall, 0.99 for f1-score, and 1.00 for specificity. This research confirms the potential of tuned SVMs in addressing complex data classification challenges and offers important insights for medical diagnostic applications.

Media pembelajaran saat ini telah berkembang, salah satu contohnya adalah media pembelajaran digital atau biasa disebut literasi digital. Literasi digital dapat berupa teks, audio, atau video. Cara mendapatkannya dapat melalui berbagai sumber seperti media sosial dan halaman web. Keuntungan dari media pembelajaran digital adalah dapat meningkatkan kemampuan belajar siswa. Guru juga dapat menggunakan berbagai sumber seperti teks, gambar, audio dan video dalam materi pembelajaran. Maka program kemitraan Masyarakat (PKM) dari Udinus menawarkan pendampingan pembuatan media pembelajaran berbasis multimedia dengan Canva. Metode yang digunakan dalam program kemitraan Masyarakat adalah praktek dengan Canva. Dalam praktek tersebut, para guru diawali membuat slide presentasi kemudian diubah menjadi video pembelajaran dengan memanfaatkan asset yang disediakan oleh Canva.

Social media is a service that is very supportive for government activities, especially in providing openness and community-based government. One form of its implementation is the Semarang City government through the Center for Community Complaints Management (P3M), whose task is to manage community complaints that enter one of the communication channels namely social media twitter. The number of public complaints that enter every day is very varied. This is certainly quite difficult for managers in categorizing complaints reports according to the relevant Local Government Organizations (OPD). This paper focuses on the problem of how to conduct clustering of community complaints. The data source comes from Twitter using the keyword "Laporhendi". Text document data from community complaint tweets was analyzed by text mining methods. A number of pre-processing of text data processing begins with the process of case folding, tokenizing, stemming, stopword removal and word robbering with tf-idf. In conducting cluster mapping, clustering algorithm will be used in dividing the complaint cluster, namely the k-means algorithm. Evaluation of cluster results is done by using purity to determine the accuracy of the results of grouping or clustering.