25 January 2018 in IOP Conference Series: Materials Science and Engineering
31 July 2024 in IEEE Access
Detecting sarcasm in text is a very challenging task. Sarcasm often depends on context, tone, and cultural references, which can be difficult for machines to understand. In addition, the increasing occurrence of code-mixing in social media posts poses new challenges in sarcasm detection. Research on sarcasm detection in mixed-code text written in languages other than English is still limited owing to the unavailability of public datasets. To overcome this issue, a dataset was built for sarcasm detection in Indonesian-English mixed-code texts. Furthermore, a hybrid model based on a convolutional neural network (CNN) with multi-head attention and a bi-directional gated recurrent unit (BiGRU), named MHA-CovBi, is proposed for sarcasm detection. In the proposed MHA-CovBi model, a combination of FastText and GloVe word embeddings is utilized to assist the model in understanding and processing texts in different languages. GloVe pretrained word embedding is used for vector representation of English words, while FastText pretrained word embedding is used for vector representation of Indonesian words. Moreover, an auxiliary pragmatic feature illustrating the number of pragmatic markers in tweets was incorporated to enhance detection performance. In addition, this study presents a language detection scheme and transliteration process that can be used to handle languages other than Indonesian and English using Google Translate API. The performance of the proposed model was evaluated through comparative analysis against existing approaches. The proposed model successfully outperformed current state-of-the-art models, achieving an accuracy of 94.60% and F1 score of 94.38%.
1 November 2019 in Journal of Physics: Conference Series
The Bangil District Court is an IB class court that handles a large number of case cases. Every year more and more case cases are included in the Bangil District Court, but not all case cases are in a mutation status. By using classification techniques that can process large amounts of data to find patterns that occur in case data. Data processing is used to predict case minutation with the decision tree method using ID3 algorithm. Case data has 8 attributes and has been classified into 6 parts, namely division based on Case Type, Register, Case Classification, Length of Process, Public Prosecutor and Decision with a goal of Mutation Status. Weka 3.6 is an API that is used to build rules / rule bases. The rule that was formed was then implemented in the making of a case status prediction application in the web-based Bangil District Court.
3 November 2016 in Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Dalam mendesain template aplikasi berbasis web, programmer web menggunakan sintaks-sintaks CSS untuk membuat tampilan menjadi lebih menarik. Dalam perkembangannya banyak tool-tool atau framework CSS yang dapat dimanfaatkan untuk mempercepat pengerjaan desain template web, diantaranya Gumby, Foundation, Less Framework, Blueprint CSS dan Twitter Bootstrap. Dari beberapa framework CSS tersebut, Twitter Bootstrap hadir dengan tutorial dan dokumentasi yang berlimpah serta memiliki fitur responsive. Pada penelitian ini penulis megimplementasikan framework Twitter Bootstrap pada perancangan aplikasi penerimaan mahasiswa baru berbasis web. Tahapan yang diambil dalam perancangan Aplikasi Penerimaan Mahasiswa Baru ini diawali dengan mendownload Twitter Bootstrap dari website resminya dan melakukan ekstraksi ke folder project setelah itu baru class-class yang disediakan oleh Twitter Bootstrap dapat dipanggil dalam pengerjaan desain aplikasi. Dengan penerapan framework twitter bootstrap ini pengerjaan desain aplikasi lebih cepat karena tidak perlu lagi memikirkan sintaks-sintaks css dan menghasilkan template yang responsive, ringan dan simple.
26 June 2024 in SMATIKA JURNAL
Indonesia with its rich cultural diversity, certainly results in the existence of various languages in it. In the dialect of a region, there are letter symbols that represent the expression of the region's unique language. One example of a language that shows unique characteristics in its writing system is Bima, known as the Bima script. Bima script, or often referred to as Mbojo script, is a writing system traditionally used in the Bima region, located in West Nusa Tenggara Province. Bima script is still not widespread among the public, so it is important to preserve it as part of the cultural heritage of the Mbojo tribe. This research aims to train a computer to recognize Bima characters. The Convolutional Neural Network (CNN) method is used in this research to recognize Bima script handwriting. The dataset used consists of 2640 images of Bima script handwriting with 22 classes. The results showed a reliable performance of the CNN model, with an accuracy of 97,34%, precision 97,56%, recall 97,34%, and f1-score 97,31% on the test data.