Spam Detection on Social Media Using Semantic Convolutional Neural Network

Jain, Gauri; Шарма, Маниша; Agarwal, Basant

doi:10.4018/ijkdb.2018010102

Cited by 54 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 10 shows the performance comparison between the proposed method and studies using similar methods available in the literature. Jain et al [9] proposed an LSTM structure to detect spam messages on twitter and used word2vec for text representation with the help of knowledge bases to enhance the representation of text by adding more semantic. Madisetty et al [23] used different word embedding methods such as word2vec and GloVe to represent text and fed into the CNN-based architecture to detect spam messages on twitter ( Figure 5).…”

Section: Discussionmentioning

confidence: 99%

“…In this study, we will focus on spam detection on the Twitter network. To detect spam on Twitter, most of the studies were oriented on two main directions, detecting spammer accounts as in [1][2][3][4][5][6], and detecting spammed tweet messages as in [7][8][9][10][11].…”

Section: Related Workmentioning

confidence: 99%

“…In [14], the authors proposed two combination models, named BLSTM-2DPooling and BLSTM-2DCNN, where the 2D max-pooling operation was applied to obtain a fixed-length representation of the text, and 2D convolution was utilized to sample more meaningful information of the matrix. In [9], the authors proposed semantic Convolutional Neural Network (SCNN) for spam classification on Twitter with the help of WordNet and ConceptNet knowledge bases, and in [15,16] the syntax of each tweet was learned through Word2Vector model and trained by deep learning, then a binary classifier was used to differentiate between spam and non-spam tweet. Table 2 summarizes some deep learning-based methods to detect spam on social networks.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Context-dependent model for spam detection on social networks

Ghanem

Erbay

2020

SN Appl. Sci.

View full text Add to dashboard Cite

Social media platforms are getting an important communication medium in our daily life, and their increasing popularity makes them an ideal platform for spammers to spread spam messages, known as spam problems. Moreover, messages on social media are vague and messy, so a good representation of the text may be the first step to address spam problem. While traditional weighting methods suffer from both high dimensionality and high sparsity problems, traditional word embedding methods suffer from context independence and out of vocabulary problems. To overcome these problems, in this study, we propose a novel architecture based on a context-dependent representation of text using the BERT model. The model was tested using the Twitter dataset, and experimental results show that the proposed method outperforms traditional weighting methods, traditional word embedding based methods as well as the existing state of the art methods used to detect spam on the twitter platform.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Context-dependent model for spam detection on social networks

Ghanem

Erbay

2020

SN Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…CNNs have produced excellent results when they were used for natural language processing (NLP) [51], computer vision [52], spam detection [53], text classification [54], topic categorisation [55], and image classification [56]. In this paper, we will use the CNN to perform binary classification on non-image or non-sequential or non-text data.…”

Section: F Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Evaluating Uses of Deep Learning Methods for Causal Inference

Whata

Chimedza

2022

IEEE Access

View full text Add to dashboard Cite

Logistic regression is a popular method that is used for estimating causal effects in observational studies using propensity scores. We examine the use of deep learning models such as the deep neural network (DNN), PropensityNet (PN), convolutional neural network (CNN), and convolutional neural network-long short-term memory network (CNN-LSTM)) to estimate propensity scores and evaluate causal inference. Deep learning models, unlike logistic regression, do not depend on assumptions regarding (i) how variables are selected, (ii) specification of the correct functional form, (iii) statistical distributions of the variables, and (iv) interactions are specified. If these assumptions are not met when using logistic regression, one may obtain biased estimates of treatment effects due to not achieving covariate balance. We conducted studies using simulated data with different sample sizes (N = 500, N = 1000, N = 2000), 15 covariates, a continuous outcome and a binary exposure. These data were used in seven scenarios that were different in the degree of nonlinearity and non-additivity associations between the exposure and covariates. The estimation of propensity scores was considered as a classification task, and performance metrics that included the classification accuracy, the receiver operating characteristic curve area under the curve (AUCROC), the covariate balance, the standard error, the absolute bias, and the 95% confidence interval coverage were evaluated for each model. Overall, CNN and CNN-LSTM achieved good results for covariate balance, classification accuracy, AUCROC, and Cohen's Kappa. Logistic regression provided substantially better bias reduction, but it had subpar performance based on classification accuracy, AUCROC, Cohen's Kappa, and 95% confidence interval coverage. The results suggest that deep learning methods, especially CNN, may be useful for estimating propensity scores that are used to estimate causal effects.

show abstract

“…On the off chance that the quantity of layers' increases, the number expands more quickly. In addition, vectorising a picture/message totally overlooks the complex 2D spatial structure of the picture/content [29]. A CNN comprises of an information and a resultant layer, just as numerous concealed layers [30].…”

Section: Proposed Workmentioning

confidence: 99%

Image Based Classification of Rumor Information from the Social Network Platform

Sreenivasulu¹,

Wajeed²

2021

View full text Add to dashboard Cite

Spam emails based on images readily evade text-based spam email filters. More and more spammers are adopting the technology. The essence of email is necessary in order to recognize image content. Web-based social networking is a method of communication between the information owner and end users for online exchanges that use social network data in the form of images and text. Nowadays, information is passed on to users in shorter time using social networks, and the spread of fraudulent material on social networks has become a major issue. It is critical to assess and decide which features the filters require to combat spammers. Spammers also insert text into photographs, causing text filters to fail. The detection of visual garbage material has become a hotspot study on spam filters on the Internet. The suggested approach includes a supplementary detection engine that uses visuals as well as text input. This paper proposed a system for the assessment of information, the detection of information on fraud-based mails and the avoidance of distribution to end users for the purpose of enhancing data protection and preventing safety problems. The proposed model utilizes Machine Learning and Convolutional Neural Network (CNN) methods to recognize and prevent fraud information being transmitted to end users.

show abstract

Spam Detection on Social Media Using Semantic Convolutional Neural Network

Cited by 54 publications

References 27 publications

Context-dependent model for spam detection on social networks

Context-dependent model for spam detection on social networks

Evaluating Uses of Deep Learning Methods for Causal Inference

Image Based Classification of Rumor Information from the Social Network Platform

Contact Info

Product

Resources

About