Skripsi

KLASIFIKASI INTENT MENGGUNAKAN SOFTMAX DAN KLASIFIKASI ENTITAS MENGGUNAKAN CONDITIONAL RANDOM FIELD PADA FRAMEWORK RASA

---

Penilaian

---

This research aims to develop a Chatbot Intent Classification and Entity Classification on the RASA Framework using the Softmax and Conditional Random Field methods. In the process of creating a chatbot, there are several problems that often arise, one of which is the low accuracy of entity classification and intent classification, which causes the chatbot to not perform as expected. These problems will be addressed using a machine learning approach with the Softmax and Conditional Random Field methods, which have been proven efficient for classifying intent and entities based on user input sentences in the chatbot. The research results show that intent classification using softmax achieved an average accuracy of 0.86, precision of 0.93, recall of 0.92, and F1-score of 0.92. Entity classification using Conditional Random Field achieved an average accuracy of 0.89, precision of 0.92, recall of 0.95, and F1-score of 0.93, using 132 test data consisting of questions or commands related to the Academic Information System of the Department of Informatics Engineering, Sriwijaya University, in the Indonesian language.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307005443	T122596	T1225962023	Central Library (Referens)	Available

Detail Information

Series Title

-

Call Number

T1225962023

Publisher

Indralaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xiv, 80 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.0151 07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Informatika
Prinsip Matematika dalam Ilmu Komputer

Specific Detail Info

-

Statement of Responsibility

FIRA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment