Ditutup

text mining dan data mining

Programnya seperti berikut..

Contoh: menormalkan kalimat tidak baku menjadi baku.

Programnya pakai bahasa python.

Input: kalimat tidak baku itu diambil pake Twitter API misal dari bulan Januari 2016-Juni 2016.

Output: kalimat baku dari inputan.

Lalu dihitung akurasi output yg keluar benar itu berapa.

Untuk lebih detailnya bisa hubungi saya mengenai jurnal acuan tentang program tersebut :)

(in english)
Task:
make a code (simple web application) about how to normalize non standard sentences (from tweet) to standard sentences (KBBI) using edit distance algorithm, phonetic matching algorithm (soundex algorithm), peter norvig algorithm.

the code using python programming language

for example:

input : non standard sentences from tweet using Twitter API from January 2016-June 2016.
Ouput: standard sentences from that input

then calculate system performance like accuracy, recall, precission, f-measure.

for the detail chat me and i will send the related journal/paper to you :) Thank you

Keahlian Data Besar, Pengumpulan Data, Python, Twitter

Lihat lebih lanjut: website text mining data mining, weka text data mining, mining text data, text data mining, data mining text resume parsing, screen scraping data mining, dataset data mining association, data mining cleaning, purchase data mining contract information, example data mining, data mining research companies, data mining marketing research, build data mining project, excel data mining project, snoopy data mining

Tentang Pemberi kerja:
( 0 ulasan ) Indonesia

ID Proyek: #11599252

2 freelancers are bidding on average Rp1555555 for this job

Rp1555555 IDR dalam 3 hari
(0 Ulasan)
0.0
Rp1555555 IDR dalam 3 hari
(0 Ulasan)
0.0