Information Gain Feature Selection Methods Research Articles

Sentiment Analysis of Public Opinion Towards Tourism in Bangkalan Regency Using Naïve Bayes Method

Sentiment analysis is natural language processing (NLP) that uses text analysis to recognize and extract opinions in text. Analysis is used to convert unstructured information into more structured information, also to determine whether an object has a positive, negative, or neutral tendency, and is an effort to facilitate decision making for tourism managers as a recommendation in developing tourist attractions. In this study, opinions were conducted on tourism reviews in Bangkalan using the Naïve Bayes method. This method is a machine learning algorithm to classify text into concepts that are easy to understand and provide accurate results with high efficiency. This method is proven to provide excellent results with a high level of accuracy, especially for large data, but has some drawbacks, sensitive to feature selection. Thus, a feature selection process is needed to improve classification efficiency by reducing the amount of data analyzed, with the Information Gain feature selection method. The word weighting method uses TF-IDF, while the data used comes from google maps reviews taken through web scraping, where tourist visitors provide reviews and ratings of places that have been visited. However, the large number of reviews can make it difficult for tourist attractions managers to manage them, so the process of labeling the sentiment class of the review data obtained 3649 reviews, with 2583 positive, 275 negative, and 457 neutral. Based on the test results that have been carried out using the Information Gain threshold of 0.0001, 0.0003, and 0.0007 can improve the accuracy of the Naïve Bayes model, for the best test at threshold 0.0007, with an accuracy value of 78.68%, precision 80.44%, recall 82.59%, and f1-score 82.53%, from the test results it shows that the use of information gain feature selection and SMOTE technique has a fairly good performance in classifying public opinion sentiment data on tourism in Bangkalan Regency, meaning that tourism management is good seen from the results of visitor satisfaction sentiment.

Feature Selection using Information Gain on the K-Nearest Neighbor (KNN) and Modified K-Nearest Neighbor (MKNN) Methods for Chronic Kidney Disease Classification

Purpose: Kidneys has an important role in the human excretory system. Unhealthy kidneys can affect kidney function. It is important to know the symptoms of chronic kidney disease. One data mining technique that can be applied is the classification technique to determine whether a person has chronic kidney disease or not based on the symptoms (attributes) obtained from medical records. The symptoms of chronic kidney disease obtained amount to 24 symptoms or attributes,Methods/Study design/approach: In this research, the classification of chronic kidney disease is performed using the information gain feature selection method and the KNN and MKNN classification methods. The number of data used is 400 data with 2 classes, namely chronic kidney disease (CKD) and non-chronic kidney disease (non-CKD).Result/Findings: Based on the test results, it was found that the hemo (Hemoglobin) attribute has the highest information gain value, which is 0.6255. The best accuracy for the KNN classification method is 96.61%, and for the MKNN method, it is 98%. Novelty/Originality/Value: The purpose of information gain feature selection is to choose features or attributes that significantly influence chronic kidney disease. Keywords: Chronic Kidney Disease, Information Gain, KNN, MKNN

COMPARISON OF FEATURE SELECTION TO PERFORMANCE IMPROVEMENT OF K-NEAREST NEIGHBOR ALGORITHM IN DATA CLASSIFICATION

One of the most widely used data classification methods is the K-Nearest Neighbor (K-NN) algorithm. Classification of data in this method is carried out based on the calculation of the closest distance to the training data as much as the value of K from its neighbors. Then the new data class is determined using the most votes system from the number of K nearest neighbors. However, the performance of this method is still lower than other data classification methods. The cause is the use of the most voting system in determining new data classes and the influence of features less relevant to the dataset. This study compares several feature selection methods in the data set to see their effects on the performance of the K-NN algorithm in data classification. The feature selection methods in this research are Information gain, Gain ratio, and Gini index. The method was tested on the Water Quality dataset from the Kaggle Repository to see the most optimal feature selection method. The test results on the dataset show that the use of the feature selection method affects to increase the performance of the K-NN algorithm. The average increase in the accuracy value obtained from the value of K=1 to K=15 is the Information Gain increased by 1.17%, Gain ratio increased by 0.69%, and the Gini index increased by 1.19%. The highest accuracy value in the classification of the Water Quality dataset is 89.66% at K=13 with the Information Gain feature selection method.

Analysis of Parkinson's Disease Using an Imbalanced-Speech Dataset by Employing Decision Tree Ensemble Methods.

Parkinson's disease (PD) currently affects approximately 10 million people worldwide. The detection of PD positive subjects is vital in terms of disease prognostics, diagnostics, management and treatment. Different types of early symptoms, such as speech impairment and changes in writing, are associated with Parkinson disease. To classify potential patients of PD, many researchers used machine learning algorithms in various datasets related to this disease. In our research, we study the dataset of the PD vocal impairment feature, which is an imbalanced dataset. We propose comparative performance evaluation using various decision tree ensemble methods, with or without oversampling techniques. In addition, we compare the performance of classifiers with different sizes of ensembles and various ratios of the minority class and the majority class with oversampling and undersampling. Finally, we combine feature selection with best-performing ensemble classifiers. The result shows that AdaBoost, random forest, and decision tree developed for the RUSBoost imbalanced dataset perform well in performance metrics such as precision, recall, F1-score, area under the receiver operating characteristic curve (AUROC) and the geometric mean. Further, feature selection methods, namely lasso and information gain, were used to screen the 10 best features using the best ensemble classifiers. AdaBoost with information gain feature selection method is the best performing ensemble method with an F1-score of 0.903.

An Optimized Approach for Predicting Water Quality Features Based on Machine Learning

Traditionally, water quality is assessed using costly laboratory and statistical methods, rendering real-time monitoring useless. Poor water quality requires a more practical and cost-effective solution. The machine learning classification approach appears promising for rapid detection and prediction of water quality. Machine learning has been used successfully to predict water quality. However, research on machine learning for water quality index (WQI) prediction is generally lacking. Therefore, this research aims to identify the important features for the WQI, which necessitated the classification of numerous indicators. This study develops four machine learning models (Artificial Neural Network, Support Vector Machine, Random Forest, and Naïve Bayes) based on the WQI and chemical parameters. The Langat Basin in Selangor dataset from the Department of Environment of Malaysia trains and validates each machine learning model. Several data preprocessing tasks such as data cleaning and feature selection have been conducted on the raw dataset to ensure the quality of the training data. The performance of these machine learning algorithms is further rectified based on the selected features set by several feature selection strategies such as information gain, correlation, and symmetrical uncertainty. Each classifier is then optimized using different tuning parameters to achieve optimum values before comparing the output of the three classifiers against each other. The observational results have shown that the optimized Random Forest classifier with the WQI parameter selected by the information gain feature selection method achieved the highest performance. The experimental results show that the WQI parameters are more relevant in predicting the WQI than the other variables. Consequently, this result shows that parameter oxygen (DO) and biochemical oxygen demand (BOD) are important features for predicting WQI. The proposed model achieved reasonable accuracy with minimal parameters, indicating that it could be used in real-time water quality detection systems.

A systematic approach to diagnose Parkinson’s disease through kinematic features extracted from handwritten drawings

Parkinson’s disease is a slowly progressing neurodegenerative disorder that is not easy to diagnose at the early stages because of delayed symptoms. The most usual ways to diagnose this disease is either by reviewing the medical history of the patient and looking at the computerized tomography scans along with the magnetic resonance imaging by a neurologist or by analyzing the body movements of the patient by the body movement analysts. However, recent research work indicates that Parkinson’s can be effectively diagnosed at an early stage by measuring the changes in handwriting. In this work, the authors have proposed a Parkinson’s disease diagnosis system by analyzing the kinematic features extracted from the handwritten spirals drawn by patients. The publicly available University of California, Irvine Parkinson’s disease spiral drawings using digitized graphics tablet dataset is used in this study. A total of 29 kinematics features are extracted from the dataset. The class imbalance problem in the dataset is handled by the synthetic minority oversampling technique because the dataset is highly imbalanced. Relevant features are selected using the genetic algorithm and mutual information gain feature selection methods. The performance of four classifiers support vector machine, random forest, AdaBoost and XGBoost are analyzed in terms of accuracy, sensitivity, specificity, precision, F-measure, and area under ROC curve. Tenfold cross-validation method is used for validating the results. The combination of mutual information gain feature selection method with AdaBoost classifiers outperforms with 96.02% accuracy.

SELEKSI FITUR INFORMATION GAIN DAN ALGORITMA NAÏVE BAYES UNTUK REVIEW OPINI KONSUMEN

The growth of internet users in Indonesia is increasing, this is in line with online shopping habits or often referred to as e-commerce which continues to increase. Various things are done by e-commerce companies to maintain customer loyalty, one of which is through product evaluation using consumer opinion reviews. The number of reviews that are too many will be biased, so it is necessary to do a classification method that will help e-commerce companies to find out the extent of their customer loyalty. Consumer review becomes something important because all assessments of the products they buy are all in the review column. In this research, a consumer review is carried out using the Naive Bayes classification method and to improve the accuracy of attributes using the Information Gain feature selection and using the Select by Weight operator which will display the best attributes of the pre processing process. The review data set is taken from consumers' comments on Google Play. The results of this study are classifying consumer reviews into positive reviews and negative reviews with Cross Validation using 10 fold, the accuracy of the Naive Bayes method is 78.4% using the Information Gain feature selection method, the accuracy increases to 81.2%

Network intrusion detection model based on multivariate correlation analysis – long short‐time memory network

For the purpose of improving the low detection performance of network intrusion detection model caused by high-dimensional data, and from the perspective of time correlation characteristics of intrusion detection datasets, the authors present a network intrusion detection model based on the multivariate correlations analysis - long short-term memory network (MCA-LSTM). Firstly, this model selects the optimal feature subsets through the information gain feature selection method, the MCA module is then used to change the feature subset into the triangle area map (TAM) matrix, and finally inputs the TAM matrix into the LSTM module for the training and testing purpose. To better demonstrate the performance of the proposed model, it is compared with those of convolutional neural networks, recurrent neural network, deep forest, support vector machine, and k-nearest neighbour methods proposed by the previous researchers. Experimental results show that the testing accuracy of the proposed model on 5-classification task using NSL-KDD dataset is up to 82.15%, and that on 10-classification task using UNSW-NB15 dataset is up to 77.74%. Moreover, compared with the traditional machine learning and existing deep learning models, the proposed model has shown to achieve better classification detection performance.

Impact of feature selection on classification via clustering techniques in software defect prediction

Software testing using software defect prediction aims to detect as many defects as possible in software before the software release. This plays an important role in ensuring quality and reliability. Software defect prediction can be modeled as a classification problem that classifies software modules into two classes: defective and non-defective; and classification algorithms are used for this process. This study investigated the impact of feature selection methods on classification via clustering techniques for software defect prediction. Three clustering techniques were selected; Farthest First Clusterer, K-Means and Make-Density Clusterer, and three feature selection methods: Chi-Square, Clustering Variation, and Information Gain were used on software defect datasets from NASA repository. The best software defect prediction model was farthest-first using information gain feature selection method with an accuracy of 78.69%, precision value of 0.804 and recall value of 0.788. The experimental results showed that the use of clustering techniques as a classifier gave a good predictive performance and feature selection methods further enhanced their performance. This indicates that classification via clustering techniques can give competitive results against standard classification methods with the advantage of not having to train any model using labeled dataset; as it can be used on the unlabeled datasets.Keywords: Classification, Clustering, Feature Selection, Software Defect PredictionVol. 26, No 1, June, 2019

Compound Emotion Recognition of Autistic Children During Meltdown Crisis Based on Deep Spatio-Temporal Analysis of Facial Geometric Features

An important contribution to computer vision applications has been made by recognizing human emotion. Although it is very significant, this work considers the security of autistic people while in meltdown crisis by introducing a new system to warn caregivers through facial expressions detection. A precautionary approach has been taken to deal with meltdown crisis. Certainly, the indications of Meltdown are linked to abnormal facial expressions related to compound emotions. Actually, researchers thought long ago that Human Facial Expressions (HFE) are not able to express more than the seven basics emotions. HFE have been considered by psychologists as very complicated one, which can indicate two or even more emotions known as compound or mixed ones. A few studies have been done concerning Compound Emotion (CE). As well as, many difficult tasks to detect Compound Emotion Recognition (CER). In this paper, we empirically assess a group of deep spatio-temporal geometric features of micro-expressions of autistic children during a meltdown crisis. To achieve this goal, we make a comparison of the CER performance and diverse collections of micro-expressions features to select the features which best differentiates autistic children CE in meltdown crisis from normal state, and the best classifier performance. We record autistic children videos in normal and meltdown crisis using Kinect camera in serious circumstances. The experimental evaluation shows that the deep spatio-temporal geometric features and Recurrent Neural Network RNN with 3 hidden layer using Information Gain Feature Selection methods provide best performance (85.8%).

PENERAPAN METODE K-NEAREST NEIGHBOR DAN INFORMATION GAIN PADA KLASIFIKASI KINERJA SISWA

Education is a very important problem in the development of a country. One way to reach the level of quality of education is to predict student academic performance. The method used is still using an ineffective way because evaluation is based solely on the educator's assessment of information on the progress of student learning. Information on the progress of student learning is not enough to form indicators in evaluating student performance and helping students and educators to make improvements in learning and teaching. K-Nearest Neighbor is an effective method for classifying student performance, but K-Nearest Neighbor has problems in terms of large vector dimensions. This study aims to predict the academic performance of students using the K-Nearest Neighbor algorithm with the Information Gain feature selection method to reduce vector dimensions. Several experiments were conducted to obtain an optimal architecture and produce accurate classifications. The results of 10 experiments with k values ​​(1 to 10) in the student performance dataset with the K-Nearest Neighbor method showed the largest average accuracy of 74.068 while the K-Nearest Neighbor and Information Gain methods obtained the highest average accuracy of 76.553. From the results of these tests it can be concluded that Information Gain can reduce vector dimensions, so that the application of K-Nearest Neighbor and Information Gain can improve the accuracy of the classification of student performance better than using the K-Nearest Neighbor method.

Sentiment classification of twitter data belonging to renewable energy using machine learning

The paper disccuses about the sentimenal analysis process which is a classification problem. To study the emotions of people about alternate energy sources, we carried out sentiment analysis on Twitter data. Sentiment analysis is used to analyze opinions of the user for decision making with the help of natural language processing techniques. In this paper, we carried out sentiment analysis and classification task of tweets belonging to #RenewableEnergy. We applied five different machine learning algorithms for the classification of tweets into three categories. We have carried classification without feature selection technique and with feature selection techniques. We have used CfsSubsetEvaluation and Information Gain feature selection methods to reduce the number of features from the dataset. The result obtained through the techniques followed in this paper, shows that the accuracy of sentiment classification is better with feature selection methods. The best accuracy (92.96%) is achieved with Support Vector Machine(Using PUK Kernel) and CfsSubsetEval feature selection method.

CWAAP: An Authorship Attribution Forensic Platform for Chinese Web Information

Illegal web information is common on the Internet. To prevent phenomena of illegal web information from happening, providing effective evidence for court to punish the criminals by means of law is one effective method. In this paper, an authorship attribution platform for Chinese web information, CWAAP, is described. Based on the language characteristics of Chinese web information, lexical features and structural features which can express the author’s writing habit are extracted. Support vector machines (SVM) are used for learning author’s writing features. To test the effectiveness of CWAAP, literature, Blog and BBS datasets are used in the experiments on the platform. Five experiments are performed. Experimental results show that lexical features and structural features are effective. The number of words in training samples should exceed 200 at least. By Information Gain feature selection methods, 800 lexical features can express the authors’ writing style. There is a small difference between the authors’ topics. All the parts of speech reserved are perfect. These results confirm that the platform is effective and feasible for cybercrime forensic.

Optimization of a Computer-Aided Detection Scheme Using a Logistic Regression Model and Information Gain Feature Selection Method

Optimization of a Computer-Aided Detection Scheme Using a Logistic Regression Model and Information Gain Feature Selection Method