Skripsi

NAMED ENTITY RECOGNITION MENGGUNAKAN PEMBOBOTAN TERM FREQUENCY - INVERSE DOCUMENT FREQUENCY DAN SUPPORT VECTOR MACHINES

---

Penilaian

---

The sources of information are currently diverse, making it easier for people to get information. However, the main information in the media is not structured so that it must be carefully read so as not to get wrong information. For that we need a tool to extract information. Named Entity Reognition (NER) or the recognition of named entities is a technique in extracting information by recognizing entities that have been determined in a sentence. In this study, NER is used in Indonesian language news texts using weighting term frequency - inverse document frequency (TF-IDF) and support vector machines (SVM) for named entities such as names of people (PER), names of organizations (ORG), names of locations (LOC). ), adverb of time (TIME) and other entities (OTH). The recognition of named entities is done by using the TF-IDF weight feature and the weight of the Part of Speech Tagging (POSTag) for each word. The test was carried out on the Indonesian language news text with a total of 1773 words and the results of the performance scores for accuracy on each entity named OTH, ORG, TIME, PER and LOC each scored 60.55%, 59.85%, 53.12%, 33.01% and 4.35%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107002635	T50784	T507842021	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T507842021

Publisher

Inderalaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Uniersitas Sriwijaya., 2021

Collation

xv, 101 hlm,: ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.707

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Komputer
Data Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment