Skripsi

KLASIFIKASI INTENT PADA CHATBOT TERAPI MENGGUNAKAN MULTINOMIAL NAIVE BAYES DAN MUTUAL INFORMATION

---

Penilaian

---

Chatbot is a program that designed to be able to interact with humans through messages or voice. The chatbot will identify the intent that will understand and recognize the statements that the user enters into the chatbot. However, the problem that often arises in chatbots is that sometimes chatbots respond to inappropriate dialogue interactions. Therefore, the classification of intents is one way to be able to categorize an intent that helps provide an appropriate response to dialogue interactions. The Multinomial Naive Bayes (MNB) method is a method that is widely used, especially in document classification. However, the more data, the more features will be processed, so the MNB process will take longer. To overcome this problem, the Mutual Information method is used to reduce the number of features. The purpose of this study was to determine the performance of the MNB classification by selecting the Mutual Information feature and the MNB classification method without selecting the Mutual Information feature. The results of the tests that have been carried out show that the MNB method by selecting the Mutual Information feature has better performance than the MNB method without the Mutual Information feature selection with an accuracy of 0,27 % and 0,53 %

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107002556	T54113	T541132021	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T541132021

Publisher

Inderalaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2021

Collation

xii, 85 hlm,: ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Pemrosesan Data, Teknik Informatika
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment