39 research outputs found
User Review Automation: Detecting Actionable Complaints on Gojek in the Play Store using the LSTM Method
Full text linkThis study aims to develop an automatic complaint detector for Gojek app reviews using Long Short Term Memory (LSTM). The dataset consists of 225,002 user reviews on the Google Play Store. The purpose of this study itself is to facilitate the service team in understanding the shortcomings of the application complained by users. Automatic complaint detection will facilitate the service team to take action to resolve the problems experienced by users. Therefore, the review data provided by users is properly processed using LSTM to create an effective and efficient detection
system. Processing is carried out using three different data sharing ratios, namely 90:10, 80:20, and 70:30 to ensure that the system is stable and effective. The accuracy results of the three data sharing ratios reached above 90%, thus proving that the system is able to detect complaints well. A pre-built dashboard is used to visualize the results of the system built using LSTM to facilitate monitoring the classification results. This system is expected to facilitate companies in detecting all user complaints and finding solutions to improve services to provide comfort for users
PREDIKSI GANGGUAN PANIK MENGGUNAKAN KNOWLEDGE DISCOVERY IN DATABASE DENGAN ALGORITMA GRADIENT BOOSTING
Full text linkIn an effort to enhance the diagnosis and intervention of panic disorder, this study develops a predictive model for determining the severity level of panic disorder using the Knowledge Discovery in Databases (KDD) approach. The dataset comprises variables such as age, gender, personal and family history, current stressors, symptom severity, impact on daily life, demographics, medical history, psychiatric history, substance use, coping mechanisms, social support, and lifestyle factors. The Gradient Boosting algorithm was employed to analyze the data and uncover complex patterns among the variables. The results indicate that the proposed model is capable of classifying the severity of panic disorder with high accuracy, aligning with findings from previous studies that utilized similar approaches. Other research also supports the effectiveness of machine learning algorithms in predicting panic attacks using data from wearable devices and mobile applications. These findings are expected to contribute to the development of decision support systems in the field of mental health.
Organizational Culture and Organizational Innovation Capability through the Mediation of Knowledge Sharing
No full textThis research aims to explore the enhancement of the organizational innovation capability (OIC) in the South Sumatra Balitbangda through the role of organizational culture (OC), with the help of knowledge sharing (KS) as an intervening variable to help South Sumatra Balitbangda, which is a supporting element of the government responsible for government innovation in the South Sumatra region, maximize their competence in innovation capability. This research uses a quantitative approach with census sampling method which covers all of Balitbangda’s active employees. The examination of the collected data uses the PLS-SEM method with a total of 53 valid questionnaire responses from Balitbangda’s employees. The results indicate that OC and KS positively and significantly influence enhancing OIC. It has also proved that KS effectively mediates the relationship between OC and OIC. This study suggests a bigger sample size and scope, and the exploration of other potential variables in enhancing innovation capabilities for future research
PENERAPAN KNOWLEDGE MANAGEMENT PADA BANK SYARIAH MANDIRI MENGGUNAKAN 5 A KNOWLEDGE MANAGEMENT PROSES FRAMEWORK
No full text Bank Syariah Mandiri (BSM) merupakan bank yang telah menerapkan Knowledge Managemen System. Knowledge Management System pada Bank Syariah Mandiri. Berdasarkan hasil kuisioner dan terdapat beberapa fitur yang belum ada yang yaitu fitur pencarian yang mudah dan rinci, alert document, ask problem solving, document show, reward dan Interface yang user friendly. Untuk membuat Knowledge Management System yang efektif diperlukan beberapa cara, yaitu diantaranya penggunaan framework atau metode yang tepat disesuaikan dengan domain Knowledge masing-masing. Penulis memilih framework yang diusulkan oleh Pancholi[1. Kemudian untuk cara yang kedua pengintegrasian teknologi penulis menggunakan algoritma string matching pada proses Knowledge sharing. Penggunaan algoritma ini bertujuan mencocokan semua Knowledge yang ada dalam Knowledge base dengan Knowledge yang ingin dicari. Hasil dari penelitian ini adalah aplikasi Knowledge Management dengan fitur pencarian menggunakan KMP.
Penerapan SMS Gateway Generator Menggunakan Metode Breadth-First Search
Full text linkAbstrak—Saat ini aplikasi SMS Gateway sudah banyak sekali digunakan diberbagai bidang. SMS gateway yang sering digunakan misalnya sms premium yang digunakan pada iklan tv, sms polling, sms akademik untuk sekolah atau universitas. Sedangkan SMS Gateway Generator ini berfungsi sebagai software yang dapat digunakan untuk membuat aplikasi SMS Gateway tersebut. Untuk membuat aplikasi SMS Gateway Generator ini diperlukan fasilitas Autorespon dan Schedule. Fasilitas Autorespon dan Schedule menggunakan salah satu metode pencarian pada Artificial Intelegence, yaitu Metode Pencarian Melebar Pertama(Breadth- First Search) Kata Kunci—SMS Gateway, BF
IMPLEMENTATIONOF WEB SEMANTIC ON KNOWLEDGE MANAGEMENT SYSTEM
Full text linkAbstract—Hitherto, previous research of string matching techniques in knowledge sharing of explicit knowledge have shown a great success. However, their implementation in a knowledge management system is still underexplored. The aim of this paper is to propose an implementation of web semantic techniques for supporting all processes in knowledge management systems and producing a better accuracy of searching knowledge within an organization. A web-based application prototype of web semantic is built and several experiments are performed in order to prove the correctness of our implementation.. Index Terms— Web Semantic; knowledge management syste
Pengenalan Gambar Menggunakan Sebagian Data Gambar
Full text linkPengenalan gambar dengan menggunakan sebagian data gambar query, sebagian data gambar query ini bisa terjadi karena bentuk gambar query yang tidak utuh atau tidak sesempurna gambar asli. Gambar asli ini adalah gambar yang ada didalam database Gambar query yang tidak utuh mungkin karena objek lain yang menutupi, atau pengambilan gambar yang tidak sempurna, atau keadaan objek itu sendiri yang mengalami Perubahan. Untuk melakukan pengenalan gambar dengan kondisi seperti tersebut diatas digunakan metode ekstraksi fitur SURF
Penerapan Knowledge Managemen System Sales And Customer Care Pada PT. Telkomsel Regional Sumbagsel
Full text linkAbstract PT. Telkomsel Regional Sumbagsel have a big desire to apply knowledge management system, Therefore documenting knowledge and The utilization need to managed well in the context of increasing performance. Applicabilitty of knowledge management in PT. Telkomsel Regional Sumbagselw here is every employe can save, documenting, and share knowledge to each other have a very good rated and give a positive effect for quality of employees. It make the employee can save and documenting and share knowledge to each other. So, the employees can access, even, to learn and discuss to other employees based on the knowledge that in the post. Then , when they needed to the knowledge , it will easy to find in the database with searching fiture in knowledge management system of web based on PT. Telkomsel Regional Sumbagsel. As for this system made using SECI. The methodology used in this study refers to the KM methodology who developed by Amrit Tiwana (1999), later , the system based web will use programming language PHP. Keywords : Knowledge Management Abstrak PT. Telkomsel Regional Sumbagsel memiliki keinginan besar untuk menerapkan Knowledge management system, oleh karena itu pendokumentasian pengetahuan dan pemanfaatannya perlu dikelola dengan baik dalam konteks peningkatan kinerja. Dapat diterapkannya knowledge management di PT Telkomsel Regional Sumbagsel ini dinilai sangat baik dan dapat berefek positif bagi kualitas pegawai. Dimana setiap pegawai dapat menyimpan dan mendokumentasikan serta sharing pengetahuan yang dimiliki, sehingga pegawai lain dapat mengakses, bahkan mempelajari dan berdiskusi dengan pegawai lain berdasarkan pengetahuan yang di-posting, kemudian saat dibutuhkan suatu pengetahuan tersebut, sangat mudah ditemukan di dalam database dengan fitur searching dalam knowledge management system berbasis web pada PT Telkomsel Regional Sumbagsel. Metodologi yang digunakan pada penelitian ini merujuk pada metodologi KM yang di kembangkan oleh Amrit Tiwana (1999), dan sistem ini nantinya berbasis web dengan menggunakan bahasa pemrograman PHP. Kata kunci: Mengelola Pengetahua
Pengenalan Gambar Menggunakan Sebagian Data Gambar
Full text linkPengenalan gambar dengan menggunakan sebagian data gambar query, sebagian data gambar query ini bisa terjadi karena bentuk gambar query yang tidak utuh atau tidak sesempurna gambar asli. Gambar asli ini adalah gambar yang ada didalam database Gambar query yang tidak utuh mungkin karena objek lain yang menutupi, atau pengambilan gambar yang tidak sempurna, atau keadaan objek itu sendiri yang mengalami perubahan. Untuk melakukan pengenalan gambar dengan kondisi seperti tersebut diatas digunakan metode ekstraksi fitur SURF
Implementation Of Naïve Bayes Algorithm In Predicting Alumni Waiting Time To Secure Employment (Case Study: Universitas Sriwijaya)
Full text linkIn education, alums' success in getting a job after graduation is a significant benchmark for educational institutions in assessing the quality of education they provide. This study aims to estimate the waiting period category of alums based on the ability of alums to graduate when they are related to the waiting period category and design software that can predict the waiting period category of alums by classification method. The method applied is CRISP-DM. The data used is tracer study data in 2021 with 4,734 records. With a significant level of 5% (0.05), it was found that the waiting period category had a positive and detrimental relationship with the variables of GPA, Waiting Period, First Work Province, First Income, Ethics, Expertise, and English language ability. In this study, 10-fold cross-validation was applied, which resulted in the accuracy of the decision tree algorithm of 84.33%, the K-NN algorithm of 75.45%, the Naive Bayes Classifier algorithm of 85.21%, and the Random Forest algorithm of 84.04%. Furthermore, a different test (T-Test) was carried out, which showed that the Naive Bayes Classifier algorithm was the most dominant algorithm among the other three algorithms so that it could classify and predict the waiting period category well. This study concludes that applying the Naïve Bayes algorithm can effectively predict the waiting period for alums to get a job. The implication of this study is the development of web-based software that educational institutions can use to analyze the waiting period of alumni, provide recommendations for educational policies, and assist students in planning better career strategies
