Skripsi

KEYPHRASE EXTRACTION PADA TEKS BERBAHASA INDONESIA MENGGUNAKAN METODE TOPICRANK

---

Penilaian

---

This study investigates the implementation as well as the performance of the application of TopicRank method on performing keyphrase extraction towards Indonesian text. The utilisation of keyphrase as one of the tools on managing the growing textual information drives the need for a relevant keyphrase extraction methodology. By developing the keyphrase extraction system, applying the extraction process towards the title and abstract of Indonesian scientific paper and utilising the comparison of the keyphrase obtained by the extraction against the keyphrase determined by the writer, performance measurement was done towards the extraction process. The matter then followed by performing comparison between the obtained performance of TopicRank extraction process that did and didn’t utilise cosine similarity at the postprocessing stage. The obtained result shows that the extraction system utilising the TopicRank method managed to obtain the acquisition of performance metrics by the magnitude of value of 0.7 for accuracy, 0.08 for precision, 0.09 for recall, and 0.09 for f-score with the parameter configuration of 5 selected keyphrases which assessed to be optimal compared to 2 other parameter configuration. Furthermore, the extraction that applied the TopicRank methodology but didn’t utilise cosine similarity at the postprocessing stage obtained relatively lower performance metrics values against the optimal potency simulated through the application of cosine similarity at the postprocessing stage. The keyphrase extraction utilising the TopicRank method performed is judged to still be improvable in order to maximise the potency of the extraction performance.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307005494	T119279	T1192792023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1192792023

Publisher

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

Collation

xix, 65 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.360 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Program aplikasi
Jurusan Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment