Spam detection in social media using convolutional and long short term memory neural network

Jain, Gauri; Шарма, Маниша; Agarwal, Basant

doi:10.1007/s10472-018-9612-z

Cited by 119 publications

(47 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Text-based 9 [18], [19], [20], [21], [22], [23], [24], [25], [26] Image-based 16 [27], [28], [29], [9], [30], [31], [32], [33], [34], [35], [17], [5], [36], [37], [38], [39] [20], [30], [34], [5], [37], [38], [39] Dredze 10 5789 spam (spam =3239 & ham = 2550) [30], [31], [33], [34], [40], [17], [5], [37], [28], [21] Enron corpus 1 Not specified [22] SMS spam 1 Not specified [18] Princeton spam corpus [20], [24], [30], [31], [41], [32],…”

Section: No Of Studies Referencementioning

confidence: 99%

“…Convolutional Neural Network has recently been used to create a text-based spam classifier with the introduction of long short time memory neural network (LSTM NN) and an accuracy of more than 92-98% has been achieved [18]. [28], [44] used KNN and Naïve Bayes to implemented his work with the Dredze image dataset.…”

Section: Spam Classification Techniques Analysis and Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Phishing Image Spam Classification Research Trends: Survey and Open Issues

Abari¹,

Fazlida²,

Khalid³

et al. 2020

IJACSA

View full text Add to dashboard Cite

Section: No Of Studies Referencementioning

confidence: 99%

Section: Spam Classification Techniques Analysis and Reviewmentioning

confidence: 99%

Phishing Image Spam Classification Research Trends: Survey and Open Issues

Abari¹,

Fazlida²,

Khalid³

et al. 2020

IJACSA

View full text Add to dashboard Cite

“…al [10] introduced an unsupervised method called Reliability-based Stochastic Approach for Link-Structure Analysis, which can be used to detect topical posts on social media. Jain et al [11] used convolutional and long short-term memory (LSTM) neural networks to detect spam in social media, while addressing the challenges of text mining on short posts.…”

Section: Related Workmentioning

confidence: 99%

Detecting Illicit Drug Ads in Google+ Using Machine Learning

Zhao

Skums

Zelikovsky

et al. 2019

Bioinformatics Research and Applications

View full text Add to dashboard Cite

Opioid abuse epidemics is a major public health emergency in the US. Social media platforms have facilitated illicit drug trading, with significant amount of drug advertisement and selling being carried out online. In order to understand dynamics of drug abuse epidemics and design efficient public health interventions, it is essential to extract and analyze data from online drug markets. In this paper, we present a computational framework for automatic detection of illicit drug ads in social media, with Google+ being used for a proof-of-concept. The proposed SVM-and CNN-based methods have been extensively validated on the large dataset containing millions of posts collected using Google+ API. Experimental results demonstrate that our methods can efficiently identify illicit drug ads with high accuracy. Both approaches have been extensively validated using the dataset containing millions of posts collected using Google+ API. Experimental results demonstrate that both methods allow for accurate identification of illicit drug ads.

show abstract

“…They analyzed both word embedding with CNN(Convolutional Neural Networks) and one method which is totally based on feature analysis and thus making the ensemble stack of deep learning models with a feature analysis machine learning model, thus they were able to produce a good result of 89% in f-measure but not so good what today a pre-trained model can produce. It is also worth noting that [11] authors described the various method like lstm and cnn to solve this problem and shown a good result from that. There is also various methods available to detect spammers if we detect spammer we can block them but some time spammer, third party app takes authorization of legitimate user and on behalf of them tweet with malicious post so it is more valuable to work on the tweet level spam detection .As natural language processing area is developing day by day researcher community is working on the solving the language related problem in more intelligent way as a human can solve, in that process more language models are being developed and tested BERT ,Open AI GPT,ELMo etc are the examples of intelligent language model.…”

Section: Related Workmentioning

confidence: 99%

Twitter Spam Detection using Pre-trained Model

2019

IJRTE

View full text Add to dashboard Cite

In the age of technology social media platform is becoming a great companion for expressing the thoughts, information, and opinion. It became the powerful tool for every person who wants to expand their networks of people beyond the physical boundation. We are living at that age where various categories of social media platform available according to work needed, it may be Facebook, LinkedIn, WhatsApp or Twitter. We are focusing our work on Twitter, It is also known as microblogging site which provides service to express the opinion in limited words. As the popularity of twitter is growing day by day users are joining the platform very fast, as it happens another side many spammers are also taking undue advantages of this platform, for any social media platform it is very important to maintain the secure, safer and trustworthy environment for their legitimate users. Twitter spams are more harmful than e-mail spam because of their higher clickthrough rate, as in the social network if someone trusted some spam a genuine post than it is higher chance that the persons in the network might also trust on that spam post and may click on it. There are plenty of methods available to handle the task of twitter spam detection problem, we are solving this problem of twitter spam at tweet level.Pre-trained models are some breakthrough in the journey of machine learning and natural language processing after their advancement they are of great help. Here we are using Bidirectional Encoder Representation from Transformer (BERT) model to solve the problem as our task is to solve the problem of imbalance dataset as well as the multilingual dataset, BERT makes a clear distinction in this type of task, the main advantage of this type’s model is that we don’t have to collect millions of data for better performance of the machine learning model.

show abstract

Spam detection in social media using convolutional and long short term memory neural network

Cited by 119 publications

References 28 publications

Phishing Image Spam Classification Research Trends: Survey and Open Issues

Phishing Image Spam Classification Research Trends: Survey and Open Issues

Detecting Illicit Drug Ads in Google+ Using Machine Learning

Twitter Spam Detection using Pre-trained Model

Contact Info

Product

Resources

About