Opinion mining is an automation technique of textual data from opinion sentence that produce sentiment information. It is also called sentiment analysis that involves the construction of a system for collecting and classifying opinions about a product review done by understanding, extracting and processing the text in an opinion sentence become positive, negative, and neutral. One of the techniques mostly used by data classification is Support Vector Machine (SVM). SVM is able to identify the separated hyper plane that maximizes the margin between two different classes. However, SVM has a weakness for parameter selection or suitable feature. In this research, the researchers made an improvement toward the previous research using combined method of feature selection in SVM through comparing three-feature selection; Genetic Algorithm, Particle Swarm Optimization, and Principal Component Analysis. It can be determined which one of the best feature selections that improve the classification accuracy of SVM. The dataset was cosmetic products review downloaded from www.amazon.com. Measurement is based on SVM accuracy by adding the feature selection method. While the evaluation used 10 Fold Cross Validation and the accuracy measurement used the Confusion Matrix and ROC Curve. The result of the measurement accuracy of SVM accuracy is obtained with average 82.00% and the average AUC 0.988. After the integration of SVM algorithm and feature selection, Genetic algorithm shows the best results with average accuracy 94.00% and the average AUC 0.984. Particle Swarm Optimization indicates the best results with average accuracy 97.00% and the average AUC 0.988. While Principal Component Analysis indicates the best results with average accuracy 83.00% and the average AUC 0.809. As conclusion, the research of SVM Algorithm showed the best accuracy improvement toward the feature selection of Particle Swarm Optimization integrated with the increased accuracy from 82.00% to 97.00%.

One of the final requirements in academic education for students is to conduct scientific research as outlined in the form of a final thesis. The large number of students taking research courses, makes the Accounting Study Program of the Faculty of Economics and Business at Mercu Buana University difficult to monitor the implementation of the thesis in every semester. With this problem, the researcher aims to build an information system to monitor the thesis that can record all the processes from the beginning of choosing the topic, taking the thesis exam and the graduation done by students. The urgent need for the development of a thesis monitoring information system is the reason for choosing a method of developing Rapid Application Development (RAD), so that the wishes of the Head of Accounting Department of the Faculty of Economics and Business at Mercu Buana University can be fulfilled immediately. The RAD stage that has been carried out is the requirement gathering stage which covers the needs of the operational environment, functional requirements, information needs, and interface requirements. The design phase consists of conceptual schema design, database design and interface design. The result of this research is a thesis monitoring system which has been tested and applied to the Accounting Study Program at Mercu Buana University. This system helps for both students in thesis consultation and the head of accounting in monitoring thesis students effectively and efficiently.

Global recession news dominates social media, particularly in Indonesia, with social news platforms on Twitter generating public responses and re-tweetings on the issue. Mining these opinions from Twitter using a sentiment analysis approach yields invaluable insights. The research stages included data collection, pre-processing, data labeling using the lexical-based method like valence aware dictionary and sentiment reasoner (VADER) and TextBlob, sampling techniques using synthetic minority oversampling technique (SMOTE) and random over sampling (ROS) before and after splitting data, and modeling using machine learning such as support vector machines (SVM), k-nearest neighbour (KNN), naive Bayes, and model evaluation. The problem is that almost 300,000 data collected from NodeXL are unbalanced. The findings show that models with balanced datasets show better model evaluation results. The sampling technique was carried out before and after splitting the data. The model evaluation results show that the Bernoulli-naive Bayes algorithm, with the VADER labeling technique, and the SMOTE sampling technique after splitting data, obtains the best accuracy of 84%, and using the ROS technique obtains an accuracy of 81%. On the other hand, with the SMOTE and ROS technique before splitting data on the SVM algorithm, it gets the best accuracy of 93% from before if only using SVM only reached 84%.

The development of technology has transformed the global economic landscape, including in the realm of Micro, Small, and Medium Enterprises (MSMEs). However, MSME actors in various villages and regions often still have limitations in understanding the importance of digitalization, especially in utilizing technology to promote their products. Therefore, this Community Engagement activity is initiated with the main goal of creating and disseminating understanding about the importance of implementing a profile website, financial management application, and logo in efforts to increase visibility and sales of products for MSME actors in the Serdang Tirta Kencana Village-Owned Enterprises (BUMDes) in Tangerang, Indonesia. The implementation method is based on Community-Based Participatory Research Program (CBPR) with the following stages are location survey, website and logo creation, socialization, and evaluation. Through close collaboration with local stakeholders from BUMDes Serdang Tirta Kencana, this activity has successfully empowered MSME actors with a strong visual identity and significant digital presence. The result is a 95% increase in the skills of MSME actors in BUMDes Serdang Tirta Kencana. It is hoped that through this activity, MSME actors can become competitive and have a positive impact on local economic growth and community empowerment

Waste management poses a serious global challenge. Indonesia, as one of the world's largest waste producers, faces significant impacts from this issue. At Bank Sampah Pamulang 25, manual transaction recording has been a major problem leading to various difficulties and data inaccuracies. To address this, the Community Partnership Program (PKM) was implemented focusing on developing the Waste Bank Financial Information System (SIKEBAS) to enhance efficiency and productivity. The research method used was Community-Based Participatory Research (CBPR), involving collaboration between local communities, students, and lecturers. Through a series of activities, the SIKEBAS website was successfully developed to automate waste and financial data recording and management. Evaluation of the implementation results showed a significant improvement in efficiency and productivity among Bank Sampah Pamulang 25 staff. Initially, 88.9 percent of participants did not understand the use of technology in transaction recording at the waste bank. However, after socialization, 75 percent of participants strongly agreed and 25 percent agreed that the SIKEBAS website facilitated the transaction process. Thus, the development of the web-based information system SIKEBAS has proven to be an effective solution to address the challenges of manual waste management.

Pertumbuhan Twitter selalu meningkat seiring berjalannya waktu, namun masih banyak kekurangan yang ditemukan, seperti sumber daya manusia yang masih belum berkembang. Metode yang digunakan dalam penelitian ini adalah metode Naïve Bayes Classifier (NBC) untuk dilakukan analisis sentimen. Untuk proses penentuan kalimat opini positif, netral atau negatif diambil dari Twitter. Penentuan ini sebagai proses pengklasifikasian. Dengan menggunakan Aplikasi Python 3.77, langkah awal adalah pengambilan data atau disebut crawling lalu di proses menggunakan Bahasa alami yang biasa disebut Natural Languange Processing (NLP) menggunakan library textblob dilanjutkan tahap preprocessing lalu menghitung Probabilitas kata. Sentimen ini untuk mengklasifikasi data tweet menggunakan library TextBlob sebanyak 100 data menghasilkan 58% positif, 37% netral, dan 4% negatif.