Classification of Social Media Text Spam Using VAE-CNN and LSTM Model

Metlapalli, Ayyappa Chakravarthi; Muthusamy, Thillaikarasi; Battula, Bhanu Prakash

doi:10.18280/isi.250605

Cited by 9 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, key information with high classification accuracy could be effectively extracted. Although CNN and its methods could effectively extract part of the key information and yielded a good classification effect, context semantics [8] was still neglected. When processing natural language, long-short-term memory (LSTM) [9] is usually used to extract the context semantics of texts.…”

Section: Introductionmentioning

confidence: 99%

Chinese Short Text Classification by ERNIE Based on LTC_Block

Zhang

Xiang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Short text classification, an important direction of the basic research of natural language processing, has extensive applications. Its effect depends on feature extraction methods and feature representation methods. This paper proposed an LTC_Block-based short text classification model named ERNIE to classify Chinese short texts and extract semantics in the corpus to address the polysemy problem in the text. In this model, LTC_Block, a double-channel structural unit composed of BiLSTM and TextCNN, was used to extract the contextual sequences and overall features of semantics, and residual connection was used to integrate features and further classify short texts. Experiments on two different datasets showed that ERNIE achieved a better classification effect than mainstream models, proving its feasibility and effectiveness.

show abstract

Section: Introductionmentioning

confidence: 99%

Chinese Short Text Classification by ERNIE Based on LTC_Block

Zhang

Xiang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…The CNN model uses convolutional kernels to extract contextual information from the text, as well as the words themselves [6]. The CNN model stems from the use of channels with convolutional steps and the application of pooling, bringing the advantages of a model with spatial invariance and a programmed high light age [7]. A desirable feature of this model is that he retains a two-dimensional spatial orientation in computer vision.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Spam Classification Based on Machine Learning Algorithm

Huang¹

2023

HSET

View full text Add to dashboard Cite

As technology continues to advance, email is used in almost every field. However, the dramatic increase in the number of spam emails has led to a growing need for accurate and powerful spam classifiers. Unfortunately, spam in its many forms is constantly being updated as the Internet evolves, and the challenge of fighting spam is enormous. With the emerging of deep learning methods, deep based algorithms are widely applied in most of the real-world scene and tasks. In this paper, we used CNN, RNN, LSTM and naïve Bayes models to implement spam filtering, and compared them based on information such as accuracy, model strengths and weaknesses. We test all the models on the public dataset and measure them by four metrics, including accuracy, precision, recall and F1-score. Finally, we conclude that the naïve bayes model achieves the best performance among all those methods, which can deal with the threat of spam efficiently.

show abstract

“…Recently, CNN has been applied to various NLP tasks [29] and has been extended to Text-CNN, which has several convolutional windows of varied sizes and has an excellent classification effect in the short-text classification task [15,26]. CNN cannot effectively capture long-term context information between discontinuous words, which is important in text models [30]. To solve this limitation, RNN and LSTM can efficiently explore the potential semantic information of text, and LSTM is more common in long texts [17].…”

Section: Research Background and Literature Reviewmentioning

confidence: 99%

Autonomous Classification and Decision-Making Support of Citizen E-Petitions Based on Bi-LSTM-CNN

Sun

Zuo

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

e increasing number of e-petition services requires accurate calculation methods to perform rapid and automated delivery. Automated text classi cation signi cantly reduces the burden of manual sorting, improving service e ciency. Moreover, existing text classi cation methods focus on improving sole models with an insu cient exploration of hybrid models. Moreover, existing research lacks combinatorial model selection schemes that yield satisfactory performance for petition classi cation applications. To address these issues, we propose a hybrid deep-learning classi cation model that can accurately classify the responsible department of a petition. First, e-petitions were collected from the Chinese bulletin board system and then cleaned, segmented, and tokenized into a sequence of words. Second, we employed the word2vec model to pretrain an embedding matrix based on the e-petition corpus. An embedding matrix maps words into vectors. Finally, a hybridized classi er based on convolutional neural networks (CNN) and bidirectional long short-term memory (Bi-LSTM) is proposed to extract features from the title and body of the petition. Compared with baseline models such as CNN, Bi-LSTM, and Bi-LSTM-CNN, the weighted F1 score of the proposed model is improved by 5.82%, 4.31%, and 1.58%, respectively. Furthermore, the proposed automated petition classi cation decision support system is available on the e-petition website and can be used to accurately deliver petitions and conduct citizen opinion analysis.

show abstract

Classification of Social Media Text Spam Using VAE-CNN and LSTM Model

Cited by 9 publications

References 35 publications

Chinese Short Text Classification by ERNIE Based on LTC_Block

Chinese Short Text Classification by ERNIE Based on LTC_Block

Spam Classification Based on Machine Learning Algorithm

Autonomous Classification and Decision-Making Support of Citizen E-Petitions Based on Bi-LSTM-CNN

Contact Info

Product

Resources

About