Implementasi Vector Space Model dalam Pembangkitan Frequently Asked Questions Otomatis dan Solusi yang Relevan untuk Keluhan Pelanggan

Aziz, Abdul; Saptono, Ristu; Suryajaya, Kartika Permatasari

doi:10.15294/sji.v2i2.5076

Cited by 6 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The searched documents are seen as vectors that have distance and direction. In the vector space model, the relevance level of the query for the searched document is based on the proximity of the document vector and the query vector [16].…”

Section: Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Document Retrieval with Spelling Correction for Weak and Fabricated Indonesian-Translated Hadith

Ramadhan

Lhaksmana

2020

RESTI

View full text Add to dashboard Cite

Hadith has several levels of authenticity, among which are weak (dhaif), and fabricated (maudhu) hadith that may not originate from the prophet Muhammad PBUH, and thus should not be considered in concluding an Islamic law (sharia). However, many such hadiths have been commonly confused as authentic hadiths among ordinary Muslims. To easily distinguish such hadiths, this paper proposes a method to check the authenticity of a hadith by comparing them with a collection of fabricated hadiths in Indonesian. The proposed method applies the vector space model and also performs spelling correction using symspell to check whether the use of spelling check can improve the accuracy of hadith retrieval, because it has never been done in previous works and typos are common on Indonesian-translated hadiths on the Web and social media raw text. The experiment result shows that the use of spell checking improves the mean average precision and recall to become 81% (from 73%) and 89% (from 80%), respectively. Therefore, the improvement in accuracy by implementing spelling correction make the hadith retrieval system more feasible and encouraged to be implemented in future works because it can correct typos that are common in the raw text on the Internet.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

“…Mean Average Precision is a score obtained from measuring system performance in a series of queries [16]. MAP represents the average value of average precision from all queries.…”

Section: | || || || (5)mentioning

confidence: 99%

Improving Document Retrieval with Spelling Correction for Weak and Fabricated Indonesian-Translated Hadith

Ramadhan

Lhaksmana

2020

RESTI

View full text Add to dashboard Cite

show abstract

“…Pada Vector Space Model, sebuah istilah dipresentasikan kedalam sebuah dimensi ruang vector. Relevansi sebuah dokumen ke sebuah query didasarkan pada similaritas diantara vektor dokumen dan vektor query biasa [4].…”

Section: Vector Space Modelunclassified

Sistem Pencarian Lontar Berbasis Web Dengan Metode Vector Space Model Pada Dinas Kebudayaan Provinsi Bali

Setiadi¹,

Sudarma²,

Khrisne³

2018

SPEKTRUM

View full text Add to dashboard Cite

This study aims to assist in the search for lontar images with Information Retrieval System built using the Vector Space Model method. The search system testing resulted in a lontar search system that received recall values: 75.4% and precision: 100% based on the graph of the receiver operating characteristic (ROC) analysis. Testing with System Usability Scale (SUS) tested at the Bali Provincial Culture Office got the highest score on statement point 1, 5 and 7 which reached 42.

show abstract

“…Selain itu, dalam tahap text preprocessing ini dilakukan tokenization. Tokenization merupakan proses pengolahan token yang terdapat dalam rangkaian teks, sehingga dokumen akan dipecah-pecah menjadi term [7]. Text mining dalam prakteknya mencari pola-pola tertentu, mengasosiasikan suatu bagian teks dengan yang lain berdasarkan aturan-aturan tertentu, katakata yang dapat mewakili sehingga dapat dilakukan analisa keterhubungan antar satu dengan yang lain [5]…”

Section: Text Preprocessingunclassified

Aplikasi Penentuan Dosen Penguji Skripsi Menggunakan Metode TF-IDF dan Vector Space Model

Siregar¹,

Sinaga²,

Arianto³

2017

Computatio

View full text Add to dashboard Cite

Pada Sekolah Tinggi Teknik PLN (STT-PLN) penentuan dosen penguji tugas akhir atau skripsimerupakan tugas dari sekretaris jurusan. Penelitian ini bertujuan untuk memberikan alternativeuntuk menentukan dosen penguji skripsi. Metode yang di terapkan untuk membangun system iniadalah text mining, TF-IDF dan Vector Space Model (VSM). Text mining untuk melakukanprocessing data, dimana data yang akan diproses adalah judul dan abstrak skripsi, sedangkanVSM untuk melakukan pengklasifikasian kompetensi, penelitian ini dapat merekomendasikantiga dosen untuk menjadi dosen penguji skripsi berdasarkan kecocokan antara judul danabstrak dengan klasifikasi Pada penelitian ini, penulis menggunakan Model pengembanganperangkat lunak CRISP-DM. Adapun fase yang dimiliki oleh CRISP-DM adalah fasepemahaman bisnis, fase pemahanman data, fase pengolahan data, fase permodelan, faseevaluasi dan fase penyebaran. Hasil dari penelitian ini memiliki akurasi 93,22%.

show abstract

Implementasi Vector Space Model dalam Pembangkitan Frequently Asked Questions Otomatis dan Solusi yang Relevan untuk Keluhan Pelanggan

Cited by 6 publications

References 3 publications

Improving Document Retrieval with Spelling Correction for Weak and Fabricated Indonesian-Translated Hadith

Improving Document Retrieval with Spelling Correction for Weak and Fabricated Indonesian-Translated Hadith

Sistem Pencarian Lontar Berbasis Web Dengan Metode Vector Space Model Pada Dinas Kebudayaan Provinsi Bali

Aplikasi Penentuan Dosen Penguji Skripsi Menggunakan Metode TF-IDF dan Vector Space Model

Contact Info

Product

Resources

About