Pinned Repositories
Algerian_dialect_dataset
In recent years, many researchers have made efforts to develop more Arabic resources (Abidi, 2019), such as datasets that enhance the development and evolution of sentiment analysis for the Arabic language. We benefit from this work to design our dataset, it allows us to save time during data collection and diversify the topics covered in the corpus by diversifying data sources. We present in this directory some dataset generated from the research work of the following authors: (Bouamor et al. 2018) for MADAR. (Mataoui et al. 2016) for “Wacht7ass” and (Chader et al. 2019) for Brandt DZ
Breast_Cancer_Classification-with-svm
convolutional-neural-network-with-handwritten-characters-arabic
Implementation of cnn with Arabic handwritten characters on the OIHACDB dataset (Off lineIsolatedHandwrittenArabicCharactersDataBase). The dataset contains 5600 images of size 128 * 128 pixels each in bmp format. Each class contains exactly 200 examples.
data-extarction-in-tweeter
the directory contains a script for extracting tweeter data using the tweepy library
Deep-learning-models-to-sentiment-analysis-in-algrian-dialects
the directory brings together very frequent deep learning models for the classification of text extracted from social networks applied to three different data sets using word embading and bag of word encoding which are: CNN, LSTM, Bi-LSTM
initial-text-preprocessing--arabic-dialect-
most comments taken from social media are neither prepared nor cleaned. In script I perform several basic operations to prepare the corpus for the next preprocessing operations
Light-Spheres
creation of reflective spheres each of a color and a size different, with a surface.
metaheuristic-methods-for-solving-the-SAT-problem
the SAT problem belongs to the Np-Complete class so All known algorithms for solving the SAT have an exponential execution time in the worst case, and are therefore unusable in practice even for instances of moderate size. Intelligent tools such as heuristics (A*, Width, Depth) or meta-heuristics which are optimization algorithms whose role is to solve difficult optimization problems (PSO Algorithm, Genetic Algorithm, ASC Algorithm, etc.). In our case we will focus on the following meta heuristic algorithms: Genetic Algorithm, ASC Algorithm, PSO. Applies to two satisfiable data set instances: CNF (uf-20 and uf-75) Which contain respectively 20 variables and 75 variables. the implementation of this solution is done in java.
MSA-Algerian_linguistic_resources
The directory gathers certain linguistic resources, used for the preprocessing of dialectal and MSA texts. these resources concern: a list of word stops: French / English / Arabic / and dialect. a list of the most frequent abbreviations on social networks, a list of imogis. A French / english lexicon.
multi-agent-document-exchange-system-in-a-social-network
the system is part of a social network for the exchange of documents between users of the same community using the SCRUM method and implementing with multi-agent systems. aims to help the user of the system throughout the process of his activity
kahinasassi's Repositories
kahinasassi/initial-text-preprocessing--arabic-dialect-
most comments taken from social media are neither prepared nor cleaned. In script I perform several basic operations to prepare the corpus for the next preprocessing operations
kahinasassi/Algerian_dialect_dataset
In recent years, many researchers have made efforts to develop more Arabic resources (Abidi, 2019), such as datasets that enhance the development and evolution of sentiment analysis for the Arabic language. We benefit from this work to design our dataset, it allows us to save time during data collection and diversify the topics covered in the corpus by diversifying data sources. We present in this directory some dataset generated from the research work of the following authors: (Bouamor et al. 2018) for MADAR. (Mataoui et al. 2016) for “Wacht7ass” and (Chader et al. 2019) for Brandt DZ
kahinasassi/Deep-learning-models-to-sentiment-analysis-in-algrian-dialects
the directory brings together very frequent deep learning models for the classification of text extracted from social networks applied to three different data sets using word embading and bag of word encoding which are: CNN, LSTM, Bi-LSTM
kahinasassi/MSA-Algerian_linguistic_resources
The directory gathers certain linguistic resources, used for the preprocessing of dialectal and MSA texts. these resources concern: a list of word stops: French / English / Arabic / and dialect. a list of the most frequent abbreviations on social networks, a list of imogis. A French / english lexicon.
kahinasassi/metaheuristic-methods-for-solving-the-SAT-problem
the SAT problem belongs to the Np-Complete class so All known algorithms for solving the SAT have an exponential execution time in the worst case, and are therefore unusable in practice even for instances of moderate size. Intelligent tools such as heuristics (A*, Width, Depth) or meta-heuristics which are optimization algorithms whose role is to solve difficult optimization problems (PSO Algorithm, Genetic Algorithm, ASC Algorithm, etc.). In our case we will focus on the following meta heuristic algorithms: Genetic Algorithm, ASC Algorithm, PSO. Applies to two satisfiable data set instances: CNF (uf-20 and uf-75) Which contain respectively 20 variables and 75 variables. the implementation of this solution is done in java.
kahinasassi/Light-Spheres
creation of reflective spheres each of a color and a size different, with a surface.
kahinasassi/Breast_Cancer_Classification-with-svm
kahinasassi/convolutional-neural-network-with-handwritten-characters-arabic
Implementation of cnn with Arabic handwritten characters on the OIHACDB dataset (Off lineIsolatedHandwrittenArabicCharactersDataBase). The dataset contains 5600 images of size 128 * 128 pixels each in bmp format. Each class contains exactly 200 examples.
kahinasassi/data-extarction-in-tweeter
the directory contains a script for extracting tweeter data using the tweepy library
kahinasassi/multi-agent-document-exchange-system-in-a-social-network
the system is part of a social network for the exchange of documents between users of the same community using the SCRUM method and implementing with multi-agent systems. aims to help the user of the system throughout the process of his activity
kahinasassi/arabic-sentiment-analysis
Sentiment Analysis in Arabic tweets
kahinasassi/arabic-stop-words
Largest list of Arabic stop words on Github. أكبر قائمة لمستبعدات الفهرسة العربية على جيت هاب
kahinasassi/arabic-text-preprocessing
In this notebook you will find all the functions that we use to process a text
kahinasassi/aravec
AraVec is a pre-trained distributed word representation (word embedding) open source project which aims to provide the Arabic NLP research community with free to use and powerful word embedding models.
kahinasassi/ArSarcasm
This repository contains the Arabic sarcasm dataset (ArSarcasm)
kahinasassi/CapsNet-Keras-Text-Classification
kahinasassi/datasets
A collection of publicly available datasets
kahinasassi/eng-edu
kahinasassi/github-profile-readme-generator
🚀 Generate GitHub profile README easily with the latest add-ons like visitors count, GitHub stats, etc using minimal UI.
kahinasassi/LINEAR-REGRESSION--LOSS-and-RIDGE--
Linear Regression With LOSS and RIDGE using sickit learn
kahinasassi/Machine-Learning-Library-
A 3 famous machine learning library : Numpy , Pandas, Matplotlib
kahinasassi/NLP-library
kahinasassi/NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
kahinasassi/odoo-training
This repository is only for odoo training purpose
kahinasassi/pyknow
PyKnow: Expert Systems for Python
kahinasassi/SVM-GAUSSIAN-KERNEL-
SVM using gaussian kernel for the binary classification of the data set winequality-white using Sickit Learn
kahinasassi/UI_adobe-xd
kahinasassi/php-eureka
A PHP client for (Spring Cloud) Netflix Eureka service registration and discovery.