Miftahul Jannah, . (2023) RANCANG BANGUN DETEKSI KONDISI EMOSI MENGGUNAKAN MODEL NATURAL LANGUAGE PROCESSING BERBASIS ANDROID DAN TELEGRAM. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (189kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB 1.pdf Download (235kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (514kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (291kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (346kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (475kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (230kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (1MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (322kB) |
Abstract
Emotions are reaction by the body due to an interaction between an individual and their environment. There is a link between negative emotions and quality of life, from physical and mental health to social activities. This research was conducted to build a system that can detect negative emotions using the Natural Language Processing (NLP) model and integrate the system with Telegram platform. The integration is expected to be a feature that can send texts contain negative emotions to the connected Telegram bot account and then to be responded quickly by doctors, psychologists, psychiatrists, or parents. Making an NLP model system in the field of deep learning using Python programming language and Tensorflow library. The model consists of an Embedding layer, Dense layer, Flatten layer and Dropout layer. The model then will be converted to tflite form, then to be integrated with the Android application. Integration in the Android application also includes the Telegram bot id that has been created. After making NLP model system, the system performance is observed and get the accuracy about 91% and the loss value is 0.31. Meanwhile, its application to Android app produces an overall system performance accuracy of 87% with a Mean Square Error error value of 0.097.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1910314022] [Pembimbing: Achmad Zuchriadi P.] [Penguji 1: Henry Binsar H. Sitorus] [Penguji 2: Fajar Rahayu] |
| Uncontrolled Keywords: | natural language processing, negative emotions, bots, deep learning, kotlin |
| Subjects: | B Philosophy. Psychology. Religion > BF Psychology H Social Sciences > HA Statistics Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Fakultas Teknik > Program Studi Teknik Elektro (S1) |
| Depositing User: | Miftahul Jannah |
| Date Deposited: | 20 Jul 2023 08:29 |
| Last Modified: | 20 Jul 2023 08:29 |
| URI: | http://repository.upnvj.ac.id/id/eprint/25305 |
Actions (login required)
 |
View Item |