Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
Bank digital memiliki potensi pasar yang cukup besar, mengingat penetrasi bank yang belum menyeluruh di Indonesia. Namun, potensi tersebut juga disertai dengan potensi masalah, terutama masalah keamanan dan privasi. Penelitian ini menggunakan konsep communication privacy management theory dan expectation-confirmation theory untuk meneliti pengaruh faktor-faktor teknologi, sosial, dan individu terhadap persepsi security dan privacy pengguna serta meneliti pengaruh persepsi security dan privacy tersebut terhadap niat keberlanjutan penggunaan aplikasi bank digital. Penelitian ini menggunakan Covariance-based structural equation modelling dan berhasil mengumpulkan 421 data responden valid dari tahap pengumpulan data yang dilakukan selama 22 hari sejak 17 September 2021 hingga 8 Oktober 2021. Hasil penelitian ini menunjukkan bahwa perceived mobile transaction security memengaruhi perceived mobile app security dan perceived mobile app security memengaruhi digital banking app continuance intention. Selain itu, perceived effectiveness of privacy policy, social influence, dan perceived privacy awareness memengaruhi perceived privacy risk. Hasil penelitian memberikan insight untuk pengguna aplikasi bank digital dan diharapkan dapat berkontribusi terhadap penelitian bank digital, khususnya di Indonesia. Hasil penelitian ini juga dapat digunakan oleh bank atau pengembang aplikasi bank digital untuk meningkatkan keamanan aplikasi dan mengambil tindakan lebih lanjut untuk meminimalisir risiko privasi pengguna. ......Digital bank applications have significant market potential in Indonesia given that bank penetration has not been comprehensive in Indonesia. However, this also comes with potential issues, especially data security and privacy issues. This study uses communication privacy theory and expectation-confirmation theory to examine the influence of technological, social, and individual factors on user perceptions of security and privacy and examines the effect of security and privacy perceptions on the intention to continue using digital banking applications. The authors used a Covariance-based structural equation modeling and got 421 valid respondent data from the data collection phase that were conducted for 22 days from September 17, 2021 and ending on October 8, 2021. The outcome indicates that perceived mobile transaction security affects perceived mobile app security and perceived mobile app security affects the intention to continue using digital banking apps. In addition, the perceived effectiveness of privacy policy, social influences, and perceived privacy awareness affect the perceived privacy risk. The results of this study provide insights for users of digital bank applications and are expected to contribute to digital bank research, especially in Indonesia. The results may also be used by bank and digital bank app developers to improve app security and take further measures to minimize user privacy risks.

Abstrak :
Kemajuan teknologi di era digital telah mempermudah akses informasi melalui internet, namun juga meningkatkan risiko penipuan digital. WhatsApp menjadi salah satu platform utama yang rawan terhadap penyebaran pesan penipuan. Dalam konteks ini, penelitian bertujuan untuk mengembangkan sistem klasifikasi pesan WhatsApp yang efektif dan efisien dalam Bahasa Indonesia guna melindungi pengguna dari penipuan digital. Model yang digunakan dalam penelitian ini adalah LSTM, Bi-LSTM, dan Bi-LSTM dengan Optimasi Bayesian. Data yang digunakan adalah dataset pesan dalam Bahasa Indonesia yang telah melalui proses pre-processing dan dibagi menjadi data training dan validation dengan rasio 15%, 20%, dan 30%. Seluruh model dilatih menggunakan parameter batch size 64, epochs 30, dan optimizer Adam. Hasil penelitian menunjukkan bahwa model Bi-LSTM dengan Optimasi Bayesian memiliki akurasi terbaik pada data split 15% sebesar 93%, sementara Bi-LSTM dan LSTM masing-masing mencapai akurasi terbaik sebesar 92% dan 91%. Pengembangan prototype sistem berhasil diintegrasikan dengan WhatsApp Web Client menggunakan library whatsapp-web.js, memungkinkan prediksi tipe pesan dan tingkat akurasi ditampilkan langsung di terminal command. Penelitian ini memberikan kontribusi signifikan dalam meningkatkan keamanan digital dan efisiensi komunikasi dengan mengidentifikasi pesan penipuan secara efektif ......Technological advancements in the digital era have facilitated access to information via the internet but have also increased the risk of digital fraud. WhatsApp has become one of the primary platforms vulnerable to the spread of fraudulent messages. In this context, this study aims to develop an effective and efficient WhatsApp message classification system in Indonesian to protect users from digital fraud. The models used in this study are LSTM, Bi-LSTM, and Bi-LSTM with Bayesian Optimization. The data used is a dataset of messages in Indonesian that have undergone pre-processing and split into training and validation data with ratios of 15%, 20%, and 30%. All models were trained using a batch size of 64, 30 epochs, and the Adam optimizer. The results showed that the Bi-LSTM model with Bayesian Optimization achieved the highest accuracy with a 15% data split at 93%, while the best Bi-LSTM and LSTM models achieved 92% and 91% accuracy, respectively. The prototype system development successfully integrated with the WhatsApp Web Client using the whatsapp-web.js library, allowing message type predictions and accuracy levels to be displayed directly in the command terminal. This study provides a significant contribution to enhancing digital security and communication efficiency by effectively identifying fraudulent messages.