PERBANDINGAN SVM DAN LSTM UNTUK MEMPREDIKSI GANGGUAN KECEMASAN (ANXIETY DISORDER)

Luthfia Ashiilah, NIM.: 19106050021 (2024) PERBANDINGAN SVM DAN LSTM UNTUK MEMPREDIKSI GANGGUAN KECEMASAN (ANXIETY DISORDER). Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (PERBANDINGAN SVM DAN LSTM UNTUK MEMPREDIKSI GANGGUAN KECEMASAN (ANXIETY DISORDER)) 19106050021_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (2MB) | Preview
	Text (PERBANDINGAN SVM DAN LSTM UNTUK MEMPREDIKSI GANGGUAN KECEMASAN (ANXIETY DISORDER)) 19106050021_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (3MB) | Request a copy

Abstract

Anxiety Disorder is a disorder that causes a person's mental health by affecting a person's feelings so that they always feel healthy and worry as if there will be bad things happening that interfere with daily activities and take place on an ongoing basis. And in today's modern era, with the changes in social media that are growing rapidly, more and more people are experiencing anxiety disorders and social media is a medium to get the latest information, for example by making tweets on Twitter or The X application. This study was conducted to predict the presence of anxiety disorder in a person based on tweets in social media Twitter. In this study will be conducted with two models of methods, Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) so that it can be compared which is better between the two methods. The Data used is data from crawling with keywords taken within a certain time range. The Data is then preprocessed and labeling process so that the data is ready to be processed in the application modeling methods Support Vector Machine (SVM) and Long Short-Term Memory (LSTM). And from these results, the performance of each method can be known and get the conclusion of what method is best to solve the case. The results of this study showed that the Support Vector Machine (SVM) and Long Short Term-Memory (LSTM) methods were successfully used to predict the presence of anxiety disorder in a person based on tweets on Twitter. The results obtained from this study, namely that to predict anxiety disorders (anxiety disorder) the use of Long Short-Term Memory (LSTM) method is superior to the Support Vector Machine from 3 existing calculation matrices, namely precision, recall, and f1-score with a value of 75%. Meanwhile, for the Support Vector Machine method, it only excels in calculating the accuracy value, which is 81%.

Share this knowledge with your friends :

Actions (login required)

View Item