相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Review
Computer Science, Artificial Intelligence
Sanaa Kaddoura et al.
Summary: The presence of spam content in social media is increasing, making the detection and control of spam text essential for improving social media security. This paper provides a detailed survey on the latest developments in spam text detection and classification, discussing techniques such as Machine Learning, Deep Learning, and text-based approaches, and the challenges encountered in spam identification.
PEERJ COMPUTER SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Ali Hosseinalipour et al.
Summary: The usage of email has increased significantly, leading to an increase in spam emails that negatively impact email systems. This study presents a new method for detecting spam emails using the Horse herd metaheuristic Optimization Algorithm (HOA). Evaluation results show that the proposed method outperforms other methods in terms of accuracy and computational complexity.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Mathematical & Computational Biology
Safaa S. I. Ismail et al.
Summary: In this modern era, email communication is considered the main professional communication pathway, but the issue of spam emails persists. This paper proposes a hybrid data processing mechanism called GDTPNLP to identify spam emails in both textual and voice-based emails, achieving higher detection rates in terms of speed, performance, cost efficiency, and accuracy.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Tian Xia et al.
Summary: This study proposes a novel category-level attention mechanism called category-learning attention for short text filtering. By dynamically calculating a category differentiation matrix, the mechanism highlights words intensely distributed in the same category. Experimental results demonstrate that this mechanism significantly improves the performance of short text filtering.
Article
Chemistry, Multidisciplinary
David Opeoluwa Oyewola et al.
Summary: This paper adopts deep learning techniques to classify supply chain pricing datasets of health medications. Bayesian optimization and All K Nearest Neighbor are used to enhance the classification model. Repeated five-fold cross-validation is applied to predict the accuracy of the models. The study shows that the combination of 1D-CNN, AllkNN, and Bayesian optimization outperforms other approaches, with an accuracy range between 61.2836% and 63.3267%.
APPLIED SCIENCES-BASEL
(2022)
Proceedings Paper
Computer Science, Interdisciplinary Applications
G. Ravi Kumar et al.
Summary: This paper proposes a particle swarm optimization-based feature selection algorithm that can generate accurate results in spam email classification. The algorithm combines decision tree, support vector machine, and Naive Bayes machine learning methods, and is evaluated using the UCI spambase dataset, with experimental results showing high accuracy.
INNOVATIVE DATA COMMUNICATION TECHNOLOGIES AND APPLICATION, ICIDCA 2021
(2022)
Article
Computer Science, Artificial Intelligence
Candice Bentejac et al.
Summary: The family of gradient boosting algorithms has been expanded with XGBoost, LightGBM, and CatBoost, which focus on reliability, efficiency, speed, and accuracy. In the comparison study, CatBoost is the best in generalization accuracy and AUC, LightGBM is the fastest but not the most accurate, and XGBoost ranks second in accuracy and training speed.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Computer Science, Artificial Intelligence
Tian Xia et al.
Summary: Short Message Service (SMS) is commonly used by people in daily life, but it is also misused by spammers. Researchers have developed rule-based and content-based filtering techniques, as well as machine learning methods, to combat spam messages. The weighted feature enhanced Hidden Markov Model (HMM) has shown significant improvement in filtering accuracy and speed.
Article
Computer Science, Information Systems
Kazi Ekramul Hoque et al.
Summary: Stock price forecasting is a challenging task due to its nonlinear and dynamic nature, where machine learning models show promise. This study evaluates eight conventional machine learning models for forecasting the stock price of eleven companies from the Saudi Stock Exchange. Results show varied impacts of hyperparameter tuning, with Support Vector Regression outperforming other models and Decision Tree and K-Nearest Neighbor performing poorly.
Proceedings Paper
Materials Science, Multidisciplinary
S. Jancy Sickory Daisy et al.
Summary: The hybrid technique combining Naive Bayes Algorithm and the Markov Random Field effectively addresses the issue of spam emails, improving accuracy and reducing time consumption.
MATERIALS TODAY-PROCEEDINGS
(2021)
Article
Computer Science, Artificial Intelligence
Bilge Kagan Dedeturk et al.
APPLIED SOFT COMPUTING
(2020)
Article
Computer Science, Artificial Intelligence
Jose R. Mendez et al.
APPLIED SOFT COMPUTING
(2019)
Review
Multidisciplinary Sciences
Emmanuel Gbenga Dada et al.
Review
Computer Science, Artificial Intelligence
Omer Sagi et al.
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY
(2018)
Article
Engineering, Multidisciplinary
Eman M. Bahgat et al.
AIN SHAMS ENGINEERING JOURNAL
(2018)
Article
Multidisciplinary Sciences
Jyh-Jian Sheu et al.
Article
Computer Science, Information Systems
Xin Liu et al.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2017)
Article
Remote Sensing
Haiyan Guan et al.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2013)
Article
Computer Science, Artificial Intelligence
L Breiman