Purpose: This research aims to improve the performance of the text classification model from previous studies, by combining the IndoBERT pre-trained model with the Long Short-Term Memory (LSTM) architecture in classifying Indonesian-language tweets into several categories. Method: The classification text based on multiclass classification was used in this research, combined with pre-trained IndoBERT namely Long Short-Term Memory (LTSM). The dataset was taken using crawling method from API Twitter. Then, it will be compared with Word2Vec-LTSM and fined-tuned IndoBERT. Result: The IndoBERT-LSTM model with the best hyperparameter combination scenario (batch size of 16, learning rate of 2e-5, and using average pooling) managed to get an F1-score of 98.90% on the unmodified dataset (0.70% increase from the Word2Vec-LSTM model and 0.40% from the fine-tuned IndoBERT model) and 92.83% on the modified dataset (4.51% increase from the Word2Vec-LSTM model and 0.69% from the fine-tuned IndoBERT model). However, the improvement from the fine-tuned IndoBERT model is not very significant and the Word2Vec-LSTM model has a much faster total training time.

This research raises the problem of teachers' difficulties in assessing elementary school units, where it is still inefficient to have to multiply or duplicate questions for the exam, the lack of transparency of grades directly by parents, the hope of class teachers in this case wants to create an application that can help in the assessment process in the education unit with one of them being able to analyze answers and questions so that the teacher automatically knows the level of those who answered correctly and answered incorrectly, then a web-based application called the Computer Assisted Test was created. This application was designed using the PHP and MySql programming languages ??and then tested using the black box method. After that, the publication was carried out publicly using a domain and hosting with the site name https://catpsut.online. With a very good response, they even want this application to be used continuously in their school and hope that it can help and answer the problems experienced by schools, especially SDN 005 Palaran. Purpose: Tujuan dalam penelitian ini adalah membantu dalam solusi yang dialami oleh pihak sekolah, baik itu kepala sekolah, guru, murid, dan orang tua dalam sistem penilaian di sekolah terkhusus SD Negeri 005 Palaran Methodology: Dalam penelitian ini merancang aplikasi Computer Assited Test (CAT) dengan menggunakan pemrograman PHP dan MySql dengan pengujian dengan metode blackbox. Results: Dalam penelitiani ini tanggapan mulai dari pihak guru kelas VI, siswa, dan orang tua mendapat respon yang sangat bagus bahkan mereka bahkan berterima kasih dengan adanya aplikasi Computer Assited Test ini bisa membnatu dalam memantau akademik anak didik dan guru bisa mengambil kebijakan kebijakan dan dapat memantau akademik pesera didiknya. Limitations: Dalam penelitian ini akan terus dikembangkan mulai dari pengembangan aplikasi yang berlanjutan. Contribution: Penelitian ini memberikan kontribusi terhadap masalah yang dialami oleh satuan pendidikan SD Negeri 005 Palaran yang dalam aplikasi Computer Assited Test ini bisa diterapkan dan bisa membantu dalam memecahkan masalah tersebut.