Hilal Ramadhan Utomo's repositories
Sentiment-Analysis-on-Indonesia-English-Code-Mixed-Data
Social media like facebook and twitter were really famous over the past decade. The users of social media has exponentially risen in some countries like Indonesia has given rise to large volumes of code-mixed data, in which users use more than one language in a single text. Data with code-mixed is often noisy because the same word is written multiple times, the words in the sentence are not clearly ordered, random abbreviations are used, and most importantly the monolingual model usually does not work well on it. In this work, the author will explore sentiment analysis on English-Indonesian code-mixed data. The approach that will be used is by utilizing a multilingual pre-trained model, mBERT. The evaluation will be performed based on the classification performance metrics: precision, recall, and F-1 score.
catatan-keuangan-harian
catatan keuangan harian yang mengitung saldo anda dari pemasukan dan pengeluaran
bounce-dynamic-crumb-snake-and-ladder
basic snake and ladder game with go language
breadth-first-search
implementing breadth first search in a directed graph using c++
car-recommendation-using-KNN
Introduction to AI assignment
clone-web-gojek
cloning gojek home website
Data-Set-Analysis-Parking-Birmingham-Data-Set
I am going to analyze and visualize some datasets. In this notebook, I am analyzing the time series dataset – Parking Birmingham downloaded from the UCI machine learning repository
multi-linked-list
implementing basic multi linked list into a program that can relate a thing with a tag,
natural-language-processing-on-kindle-text-review
In this first experiment, we were asked to explore and experiment with language modeling with N-grams and neural-based ones. The corpus we use for both methods is all_kindle_review.csv, an English text corpus containing book reviews including the rate or value of each book by the reviewer. There is a data that contains reviews and readers' feelings towards a kindle book. They also give a rating to the book. Then the data will be classified based on the rating they provide, and find predictions with the new Metadata review: salty = ID of product helpful = indicates how helpful the rating given example: 8/10. rating = Rating of the product. reviewText = reviews from users. reviewTime = time spent reviewing. reviewerID = ID of reviewer reviewerName = name of the reviewer. summary = brief note from the reviewer. unixReviewTime = timestamp. The programming language we use is Python.
Used-Car-interest
Tugas clustering (unsupervised Learning) adalah mengelompokkan pelanggan berdasarkan data pelanggan di dealer tanpa memperhatikan label kelas apakah pelanggan tertarik untuk membeli kendaraan baru atau tidak. Tugas classification (supervised learning) adalah memprediksi apakah pelanggan tertarik untuk membeli kendaraan baru atau tidak berdasarkan data pelanggan di dealer.