Preferred Language
Articles
/
ijs-5018
Data Mining Methods for Extracting Rumors Using Social Analysis Tools
...Show More Authors

       Rumors are typically described as remarks whose true value is unknown. A rumor on social media has the potential to spread erroneous information to a large group of individuals. Those false facts will influence decision-making in a variety of societies. In online social media, where enormous amounts of information are simply distributed over a large network of sources with unverified authority, detecting rumors is critical. This research proposes that rumor detection be done using Natural Language Processing (NLP) tools as well as six distinct Machine Learning (ML) methods (Nave Bayes (NB), random forest (RF), K-nearest neighbor (KNN), Logistic Regression (LR), Stochastic Gradient Descent (SGD) and Decision Tree (DT)). The data set size for the suggested experiment was 16,865 samples. For pre-processing tokenization was used to separates each one of the tokens from the others. Normalization that removes all non-word tokens, deleting stop words was utilized to remove all unnecessary words, and stemming was used to obtain the stem of the tokens. Prior to using the six classification algorithms, the major feature extraction approach Term Frequency- Inverse Document Frequency (TF-IDF) was applied. The RF classifier performed better compared to all other classifiers with an accuracy of 99%, according to the data.

Keywords: Machine learning, Text classification, Naïve Byes, RF, KNN, DT, Natural language processing, SGD).

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Sun Oct 01 2017
Journal Name
International Journal Of Computer Science And Information Security (ijcsis)
Finite State Automata Generator for DNA Motif Template as Preparation Step for Motif Mining
...Show More Authors

There are many tools and S/W systems to generate finite state automata, FSA, due to its importance in modeling and simulation and its wide variety of applications. However, no appropriate tool that can generate finite state automata, FSA, for DNA motif template due to the huge size of the motif template. In addition to the optional paths in the motif structure which are represented by the gap. These reasons lead to the unavailability of the specifications of the automata to be generated. This absence of specifications makes the generating process very difficult. This paper presents a novel algorithm to construct FSAs for DNA motif templates. This research is the first research presents the problem of generating FSAs for DNA motif temp

... Show More
Preview PDF
Publication Date
Mon Jun 19 2023
Journal Name
Journal Of Engineering
Data Classification using Quantum Neural Network
...Show More Authors

In this paper, integrated quantum neural network (QNN), which is a class of feedforward

neural networks (FFNN’s), is performed through emerging quantum computing (QC) with artificial neural network(ANN) classifier. It is used in data classification technique, and here iris flower data is used as a classification signals. For this purpose independent component analysis (ICA) is used as a feature extraction technique after normalization of these signals, the architecture of (QNN’s) has inherently built in fuzzy, hidden units of these networks (QNN’s) to develop quantized representations of sample information provided by the training data set in various graded levels of certainty. Experimental results presented here show that

... Show More
View Publication Preview PDF
Crossref
Publication Date
Fri Jul 01 2022
Journal Name
Iraqi Journal Of Science
Statistical Analysis of Extreme Rainfall Data in Baghdad City
...Show More Authors

Studying extreme precipitation is very important in Iraq. In particular, the last decade witnessed an increasing trend in extreme precipitation as the climate change. Some of which caused a disastrous consequences on social and economic environment in many parts of the country. In this paper a statistical analysis of rainfall data is performed. Annual maximum rainfall data obtained from monthly records for a period of 127 years (1887-2013 inclusive) at Baghdad metrology station have been analyzed. The three distributions chosen to fit the data were Gumbel, Fréchet and the generalized Extreme Value (GEV) distribution. Using the maximum likelihood method, results showed that the GEV distribution was the best followed by Fréchet distribut

... Show More
View Publication Preview PDF
Publication Date
Sat Apr 30 2022
Journal Name
Iraqi Journal Of Science
2D Seismic Data Analysis of Judaida Structure, Northern Iraq
...Show More Authors

This research aims to study the structural analysis of the 2D reflection seismic data for the Judaida subsurface structure located in Kirkuk province, northern Iraq. It is located 60 Km southwest of Kirkuk oil field, and 35 Km southwest of Jambur oil field, the Daquq River passes through the study area. The reflectors in the seismic section were picked and identified by using the synthetic seismograms generated from the logs data of the Jd-1 well. Three main seismic reflectors, Fatha, Jeribe, and the Euphrates were chosen. These mentioned sedimentary formations were deposited during the Middle Miocene, Lower Miocene, and Early-Mid Miocene respectively. Time and depth maps were drawn for these three reflectors by processing average data f

... Show More
View Publication Preview PDF
Scopus (1)
Scopus Crossref
Publication Date
Sat Dec 30 2023
Journal Name
Iraqi Journal Of Science
Geospatial Data Analysis of School Distribution in Baghdad City
...Show More Authors

     Education and lifelong learning are necessary components of daily city life for urban communities to encourage sustainable and positive communities. The study attempts to analyze the actual school distribution patterns and densities in Baghdad, the Iraqi capital. The significance of this study is that it is associated with one of the essential aspects of humanity: the improvement and affluence of schooling; it impacts school attendance limitations and educational evolution. The education process has been inextricably tied to students' timely and orderly entrance to their schools. Hence the decision maker and planner are concerned by this. The statistics examined elementary and high schools, and the investigated

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Wed Dec 30 2020
Journal Name
Iraqi Journal Of Science
A Comparison of Different Estimation Methods to Handle Missing Data in Explanatory Variables
...Show More Authors

Missing data is one of the problems that may occur in regression models. This problem is usually handled by deletion mechanism available in statistical software. This method reduces statistical inference values because deletion affects sample size. In this paper, Expectation Maximization algorithm (EM), Multicycle-Expectation-Conditional Maximization algorithm (MC-ECM), Expectation-Conditional Maximization Either (ECME), and Recurrent Neural Networks (RNN) are used to estimate multiple regression models when explanatory variables have some missing values. Experimental dataset were generated using Visual Basic programming language with missing values of explanatory variables according to a missing mechanism at random general pattern and s

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Sun Jun 01 2014
Journal Name
Journal Of Economics And Administrative Sciences
Comparing Bayesian methods to estimate the failure probability for electronic systems in case the life time data are not available
...Show More Authors

In this research, we find the Bayesian formulas and the estimation of Bayesian expectation for product system of Atlas Company.  The units of the system have been examined by helping the technical staff at the company and by providing a real data the company which manufacturer the system.  This real data include the failed units for each drawn sample, which represents the total number of the manufacturer units by the company system.  We calculate the range for each estimator by using the Maximum Likelihood estimator.  We obtain that the expectation-Bayesian estimation is better than the Bayesian estimator of the different partially samples which were drawn from the product system after  it checked by the

... Show More
View Publication Preview PDF
Crossref
Publication Date
Wed Oct 17 2018
Journal Name
Journal Of Economics And Administrative Sciences
The Use Of Some Parametric And Non parametric Methods For Analysis Of Factorial Experiments With Application
...Show More Authors

summary

In this search, we examined the factorial experiments and the study of the significance of the main effects, the interaction of the factors and their simple effects by the F test (ANOVA) for analyze the data of the factorial experience. It is also known that the analysis of variance requires several assumptions to achieve them, Therefore, in case of violation of one of these conditions we conduct a transform to the data in order to match or achieve the conditions of analysis of variance, but it was noted that these transfers do not produce accurate results, so we resort to tests or non-parametric methods that work as a solution or alternative to the parametric tests , these method

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sat Dec 30 2023
Journal Name
Iraqi Journal Of Science
A Review for Arabic Sentiment Analysis Using Deep Learning
...Show More Authors

     Sentiment Analysis is a research field that studies human opinion, sentiment, evaluation, and emotions towards entities such as products, services, organizations, events, topics, and their attributes. It is also a task of natural language processing. However, sentiment analysis research has mainly been carried out for the English language. Although the Arabic language is one of the most used languages on the Internet, only a few studies have focused on Arabic language sentiment analysis.

     In this paper, a review of the most important research works in the field of Arabic text sentiment analysis using deep learning algorithms is presented. This review illustrates the main steps used in these studies, which include

... Show More
View Publication Preview PDF
Scopus (2)
Scopus Crossref
Publication Date
Mon Sep 23 2019
Journal Name
Baghdad Science Journal
Hazard Rate Estimation Using Varying Kernel Function for Censored Data Type I
...Show More Authors

     In this research, several estimators concerning the estimation are introduced. These estimators are closely related to the hazard function by using one of the nonparametric methods namely the kernel function for censored data type with varying bandwidth and kernel boundary. Two types of bandwidth are used:  local bandwidth and global bandwidth. Moreover, four types of boundary kernel are used namely: Rectangle, Epanechnikov, Biquadratic and Triquadratic and the proposed function was employed with all kernel functions. Two different simulation techniques are also used for two experiments to compare these estimators. In most of the cases, the results have proved that the local bandwidth is the best for all the

... Show More
View Publication Preview PDF