Light Gradient Boosting Machine for General Sentiment Classification on Short Texts: A Comparative Evaluation

Alzamzami, Fatimah; Hoda, Mohamad; Saddik, Abdulmotaleb El

doi:10.1109/access.2020.2997330

Cited by 113 publications

(57 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of Auto AI ensures that the ML process generates the most accurate and optimal predictive results that effectively scales with time and resources. Several supervised classification algorithms such as Decision Tree Classifier [22], Extremely randomized Trees (Extra Trees) Classifier [23], Gradient Boosting Classifier [24], XGBoost (XGB) [25], Light Gradient Boosting Machine (LGBM) Classifier [26], and Random Forest Classifier [27]. Boosting makes a classifier strongly correlated with the true classification.…”

Section: Journal Of Computer Sciences and Applicationsmentioning

confidence: 99%

Detecting Malicious DNS over HTTPS Traffic in Domain Name System using Machine Learning Classifiers

Banadaki¹

2020

JCSA

View full text Add to dashboard Cite

This paper presents a systematic two-layer approach for detecting DNS over HTTPS (DoH) traffic and distinguishing Benign-DoH traffic from Malicious-DoH traffic using six machine learning algorithms. The capability of machine learning classifiers is evaluated considering their accuracy, precision, recall, and F-score, confusion matrices, ROC curves, and feature importance. The results show that LGBM and XGBoost algorithms outperform the other algorithms in almost all the classification metrics reaching the maximum accuracy of 100% in the classification tasks of layers 1 and 2.LGBM algorithms only misclassified one DoH traffic test as non-DoH out of 4000 test datasets. It has also found that out of 34 features extracted from the CIRA-CIC-DoHBrw-2020 dataset, SourceIP is the critical feature for classifying DoH traffic from non-DoH traffic in layer one followed by DestinationIP feature. However, only DestinationIP is an important feature for LGBM and gradient boosting algorithms when classifying Benign-DoH from Malicious-DoH traffic in layer 2.

show abstract

Section: Journal Of Computer Sciences and Applicationsmentioning

confidence: 99%

Detecting Malicious DNS over HTTPS Traffic in Domain Name System using Machine Learning Classifiers

Banadaki¹

2020

JCSA

View full text Add to dashboard Cite

show abstract

“…Otherhand, AdaBoost has the capability to mapping data, which is hard to classify into class [18]. Gradient boosting works well when it is using uni-gram features [19].…”

Section: Literature Reviewmentioning

confidence: 99%

Comparison of the Effects of Feature Selection and Tree-Based Ensemble Machine Learning for Sentiment Analysis on Indonesian YouTube Comments

Khomsah¹,

Hidayatullah

Aribowo

2021

Proceedings of the 1st International Conference on Electronics, Biomedical Engineering, and Health Informatics

View full text Add to dashboard Cite

The main problems in sentiment analysis models on Indonesian YouTube comments are unstructured data and low classification accuracy. Sentiment analysis for Indonesian, which is different from English, requires proper preprocessing and classification methods. Previous research usually using Linear Support Vector Machine (SVM), Naïve Bayes and Decision Tree. Although the accuracy of SVM is better than other algorithms, it still needs to be improved. This study aims to compare the performance of the tree-based ensemble method and feature selection to improve the sentiment analysis model for Indonesian YouTube comments. This research crawled Indonesian YouTube comments from different domains and produce ten datasets. The preprocessing's method in this research was removed stopword, convert slang words, and stemming. For feature selection, we tested two vectorizer method, i.e. Term Frequency (TF) or Term Frequency/Inverse Document Frequency (TF-IDF). The model build using six machine learning, consist of four tree-based ensemble machine learning to raise better accuracy, Linear SVM and Decision Tree. We use tree-based ensemble machine learning, they are Random Forest, and Extra Tree represents bagging ensemble. AdaBoost and Gradient Boosting represent boosting ensemble. SVM and Decision tree as a comparison. Based on experiments by combining feature selection and ensemble machine learning, it can be concluded that the type of vectorizer has little effect on

show abstract

“…Furthermore, the authors of [25] also proposed machine learning for sentiment analysis by using text and message data in English and Chinese from micro-blogs to match in sentiment classes and then provided an indication represented by an emoticon-the performance obtained the accuracy of 88.30%. The authors of [26] considered that the conversation in social networking has several topics for which the researchers established multi-sentiment classification using the proposed machine learning method trained with a domain sentiment media dataset. The proposed model gained an overall sentiment classification accuracy of 71.79%.…”

Section: Related Workmentioning

confidence: 99%

Sentiment Level Evaluation of 3D Handicraft Products Application for Smartphones Usage

2021

View full text Add to dashboard Cite

Three-dimensional (3D) technology has attracted users’ attention because it creates objects that can interact with a given product in a system. Nowadays, Thailand’s government encourages sustainability projects through advertising, trade shows and information systems for small rural entrepreneurship. However, the government’s systems do not include virtual products with a 3D display. The objective of this study was four-fold: (1) develop a prototype of 3D handicraft product application for smartphones; (2) create an online questionnaire to collect user usage assessment data in terms of five sentiment levels—strongly negative, negative, neutral, positive and strongly positive—in response to the usage of the proposed 3D application; (3) evaluate users’ sentiment level in 3D handicraft product application usage; and (4) investigate attracting users’ attention to handicraft products after using the proposed 3D handicraft product application. The results indicate that 78.87% of participants’ sentiment was positive and strongly positive under accept using 3D handicraft product application, and evaluations in terms of assessing attention paid by participants to the handicraft products revealed that positive and strongly positive sentiment was described by 79.61% of participants. The participants’ evaluation results in this study prove that our proposed 3D handicraft product application affected users by attracting their attention towards handicraft products.

show abstract

Light Gradient Boosting Machine for General Sentiment Classification on Short Texts: A Comparative Evaluation

Cited by 113 publications

References 43 publications

Detecting Malicious DNS over HTTPS Traffic in Domain Name System using Machine Learning Classifiers

Detecting Malicious DNS over HTTPS Traffic in Domain Name System using Machine Learning Classifiers

Comparison of the Effects of Feature Selection and Tree-Based Ensemble Machine Learning for Sentiment Analysis on Indonesian YouTube Comments

Sentiment Level Evaluation of 3D Handicraft Products Application for Smartphones Usage

Contact Info

Product

Resources

About