Ekstraksi dan Analisis Produk di Marketplace Secara Otomatis dengan Memanfaatkan Teknologi Web Crawling

Husada, Ivan Nathaniel; Fernando, Edward Hanafi; Sagala, Hetthroh; Budiman, Ariel Elbert; Toba, Hapnes

doi:10.28932/jutisi.v5i3.1977

Cited by 5 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Web scraping, also known as web harvesting, web data extraction, or web mining (Husada et al, 2019), is an artificial intelligence activity that involves extracting semistructured documents from the internet, such as web pages written in markup languages like HTML or XHTML, using specialized software or scripts (Mufidah, 2022). This activity entails constructing agents to automatically download, parse, and organize data from web pages.…”

Section: Web Scrapingmentioning

confidence: 99%

Enriching Grammatical Understanding of Using Japanese Part of Speech in Dokkai Learning with the AI-Powered Oyomi Application

Mahira,

Pratiwi,

Putri

et al. 2024

PJISE

View full text Add to dashboard Cite

This research focuses on the impact of the Oyomi application on the comprehension of Japanese word classes (part of speech) and sentence structures. The primary issue addressed is the need for efficient and effective language learning tools. The objective is to explore the role of artificial intelligence (AI) within the application in enhancing Dokkai learning. The methodology encompasses a comprehensive analysis of the two principal features contributing to Dokkai learning, the utilization of AI technologies, and a comparison between traditional learning vs AI-powered mobile learning methods. Data collection involved simple linear regression statistical analysis using an F-test and correlation coefficient to gauge the relationship between the usage of the AI-powered Oyomi application and the comprehension of word classes in Dokkai learning. The F test results of 0.01 < 0.05 indicate a significant contribution and a correlation coefficient of 0.8 means the strength of the relationship is very strong. These findings show that AI, when integrated into language learning applications like Oyomi, can provide a more efficient and effective learning experience, especially in Japanese reading comprehension.

show abstract

Section: Web Scrapingmentioning

confidence: 99%

Enriching Grammatical Understanding of Using Japanese Part of Speech in Dokkai Learning with the AI-Powered Oyomi Application

Mahira,

Pratiwi,

Putri

et al. 2024

PJISE

View full text Add to dashboard Cite

show abstract

“…In this study, splash and scrapy were used to extract the data that had been searched thoroughly. The extracted data can be collected in a dataset with the help of a database [13].…”

Section: The Comprehensive Theoretical Basismentioning

confidence: 99%

DarkWeb Crawling using Focused and Classified Algorithm

Yunelfi

Purwanto²,

Ruriawan³

et al. 2022

CEPAT

View full text Add to dashboard Cite

At this moment there are more and more cases of illegal goods transactions and personal data being leaked. Illegal transactions and personal sales data are usually carried out on the deep web, especially dark web because the web has multiple layers of encryption and an anonymous system when accessing it. without any illegal transactions and personal sales data, basically the web is very wide and deep. Therefore, the crawling method can be used to explore the dark web. The crawling method on the dark web can use a crawl focus that takes a focused approach on a particular topic. The focus crawling method takes a URL approach by looking at URL that are interconnected with the main URL page on the desired topic. To do focus crawling, it is done by entering keywords that best match the desired topic. With the focus crawling method, it is hoped that the maximum URL data set related to a particular topic can be generated. From the results obtained on the crawling system on the dark web, it is hoped that it can also be used to find out the number of URLs related to certain topics. In addition, the results of this crawl can also be a source of information for further research on the dark web.

show abstract

“…Teknik crawling data merupakan kegiatan berpindah-pindah di antara halaman web secara otomatis selama web scrapping bekerja. Crawling adalah aktifitas dalam membuat Salinan dalam porsi yang relevan yang diambil dari sebuah World Wide Web [7]. Teknik crawling data juga merupakaan Teknik pengumpulan data dengan filter yang digunakan.…”

Section: Data Primerunclassified

Model Latent Dirichlet Allocation Pada Perilaku Siswa Menggunakan Media Pembelajaran Daring

Prakerti

Claresta

Ibrahim

et al. 2020

Journal of Information Management

View full text Add to dashboard Cite

Abstrak: Indonesia saat ini sedang dihebohkan dengan yang namanya sekolah Daring. Dimana yang seharusnya sekolah adalah tempat untuk guru dan siswa mengajarkan ilmu dari pendidikan hingga perilaku secara tatap muka dan sekarang karena keadaan yang tidak bisa dihindari maka harus dilakukannya pembelajaran secara online yaitu dengan alat perantara. Permasalahan diambil dari banyaknya siswa sudah mempunyai alat komunikasi yaitu handphone dan berbagai media sosial yang sudah dikuasai seperti Instagram. Dengan maksud untuk menganalisa siswa khususnya di Indonesia, sikap apa yang diambil ketika siswa menggunakan Instagram ketika sedang berlangsungnya pembelajaran secara daring. Didapatkan hasil ketika melakukan Teknik crawling data untuk mendapatkan teks atau caption dari penggunaan hashtag sekolah daring yaitu 120 post dalam keadaan sudah terseleksi dari yang bukan post dari siswa. Bentuk analisa untuk pengolahan data yang sudah didapat menggunakan model Latent Dirichlet Allocation (LDA) yaitu untuk menemukan topik yang mendominasi dari hashtag yang digunakan dengan penambahan fitur Stopword untuk kata yang tidak diperlukan. Hasil akhir dari analisa tersebut terdapat 4 topik yang dominan dan dimayoritasi oleh siswa yang mendapatkan penugasan dari sekolah seperti pelajaran biologi. Kata kunci: Instagram, Latent Dirichlet Allocation (LDA), Pembelajaran Daring, Abstract: Indonesia is currently being shocked by the named school Online. Where the school should be a place for teachers and students to teach knowledge from education to face-to-face behavior and now because of circumstances that cannot be avoided,learning must be carried out online, namely with an intermediary tool. The problem is taken from the number of students who already have communication tools, namely mobile phones and various social media that have been mastered such as Instagram. With a view to analyzing students, especially in Indonesia, what attitudes are taken when students use Instagram when learning is taking place online. Obtained results when performing techniques crawling data to get text or captions from the use hashtags, of online school namely 120 posts in a selected state from non- posts student. The form of analysis for processing the data that has been obtained uses the model, Latent Dirichlet Allocation (LDA) which is to find the dominant topic of the hashtags used by adding the feature Stopword for unnecessary words. The final result of the analysis, there are 4 topics that are dominant and are majored by students who get assignments from schools such as biology lessons. Keywords: E-Learning, Instagram, Latent Dirichlet Allocation (LDA).

show abstract

Ekstraksi dan Analisis Produk di Marketplace Secara Otomatis dengan Memanfaatkan Teknologi Web Crawling

Cited by 5 publications

References 4 publications

Enriching Grammatical Understanding of Using Japanese Part of Speech in Dokkai Learning with the AI-Powered Oyomi Application

Enriching Grammatical Understanding of Using Japanese Part of Speech in Dokkai Learning with the AI-Powered Oyomi Application

DarkWeb Crawling using Focused and Classified Algorithm

Model Latent Dirichlet Allocation Pada Perilaku Siswa Menggunakan Media Pembelajaran Daring

Contact Info

Product

Resources

About