Optimizing semantic LSTM for spam detection

Jain, Gauri; Шарма, Маниша; Agarwal, Basant

doi:10.1007/s41870-018-0157-5

Cited by 87 publications

(52 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 3 and Fig. 10 provide a contrast between RMDL's accuracy and the best accuracy in the four deep learning articles [8][9][10][11] listed in the related work section. Using complicated 3CNN architecture in [8], the best accuracy was achieved.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…In addition, some research has been presented in [8][9][10][11] on deep learning approaches for the detection of SMS spam. Using text information only, CNN and LSTM were tested in [8].…”

Section: Related Workmentioning

confidence: 99%

“…The results obtained indicated that the architecture of the CNN was superior to the architecture of the LSTM. Three models are presented in [9]: RNN, LSTM, and Semantic LSTM (SLSTM). SLTSM uses the semantic layer on top of the LSTM.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

The Impact of Deep Learning Techniques on SMS Spam Filtering

Gomaa¹

2020

IJACSA

View full text Add to dashboard Cite

Over the past decade, phone calls and bulk SMS have been fashionable. Although many advertisers assume that SMS has died, it is still alive. It is one of the simplest and most cost-effective marketing tools for companies to communicate on a personal level to their customers. The spread of SMS has led to the risk of spam. Most of the previous studies that attempted to detect spam were based on manually extracted features using classical machine learning classifiers. This paper explores the impact of applying various deep learning techniques on SMS spam filtering; by comparing the results of seven different deep neural network architectures and six classifiers for classical machine learning. Proposed methodologies are based on the automatic extraction of the required features. On a benchmark data set consisting of 5574 records, a fabulous accuracy of 99.26% has been resulted using Random Multimodel Deep Learning (RMDL) architecture.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

“…In addition, some research has been presented in [8][9][10][11] on deep learning approaches for the detection of SMS spam. Using text information only, CNN and LSTM were tested in [8].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

The Impact of Deep Learning Techniques on SMS Spam Filtering

Gomaa¹

2020

IJACSA

View full text Add to dashboard Cite

show abstract

“…The main purpose of this analysis is to infer a latent attribute of such user. Several works have been done on a single and specific perspective such as organization detection [1,3,4,5], bot detection [2,6,7,8,9], political orientation [10], age prediction [11] etc. Twitter user classification approaches involve three major types, mainly statistical-based approaches, content-based approaches and hybrid-based approaches.…”

Section: Related Workmentioning

confidence: 99%

“…They used parameters from different linguistic aspects of tweet content, this yielded F1-measure result of 89.20% for the English tweets. In [7], the authors classify tweets belonging to humans or bots. They used word2vec, Wordnet and Conceptnet to create a semantic word vector, which is used later by the Long Short Term Memory (LSTM) for the classification task.…”

Section: Related Workmentioning

confidence: 99%

Organization, Bot, or Human: Towards an Efficient Twitter User Classification

Daouadi¹,

Rebaï²,

Amous³

2019

CyS

View full text Add to dashboard Cite

Today, through Twitter, researchers propose approaches for classifying user accounts. However, they have to face confidence challenges owing to the diversity of the types of data propagated throughout Twitter. In addition, the messages from Twitter are imprecise, very short and even written in many dialects and languages. Moreover, the majority of the related works focus on the overall user's activity, which makes them not suitable at the post-level classification. This paper presents an alternative approach for classifying user accounts as being accounts of bots, humans or organizations. The suggested approach consists in accurately classifying user accounts from one single post by leveraging a minimal number of language-independent features. We performed several experiments over a Twitter datasets and supervised learn-based algorithms. Our results demonstrated that simply using a minimal number of language-independent features extracted from one single post is sufficient to classify user accounts accurately and quickly. Our proposed approach yielded high F1-measure (>95%) and high AUC (>99%) using Random Forest.Keywords. Social network analysis, twitter user classification, human vs. bot vs. organization, statisticalbased approach, content-based approach, hybrid-based approach.Human 0,939 0,940 0,939 0.993 Bot 0,986 0,977 0,981 0.995 Organization 0,888 0,919 0,902 0.992

show abstract

Recurrent Neural Networks (RNNs): Architectures, Training Tricks, and Introduction to Influential Research

Das,

Tariq,

Santos

et al. 2023

Machine Learning for Brain Disorders

View full text Add to dashboard Cite

Recurrent neural networks (RNNs) are neural network architectures with hidden state and which use feedback loops to process a sequence of data that ultimately informs the final output. Therefore, RNN models can recognize sequential characteristics in the data and help to predict the next likely data point in the data sequence. Leveraging the power of sequential data processing, RNN use cases tend to be connected to either language models or time-series data analysis. However, multiple popular RNN architectures have been introduced in the field, starting from SimpleRNN and LSTM to deep RNN, and applied in different experimental settings. In this chapter, we will present six distinct RNN architectures and will highlight the pros and cons of each model. Afterward, we will discuss real-life tips and tricks for training the RNN models. Finally, we will present four popular language modeling applications of the RNN models –text classification, summarization, machine translation, and image-to-text translation– thereby demonstrating influential research in the field.

show abstract

Optimizing semantic LSTM for spam detection

Cited by 87 publications

References 19 publications

The Impact of Deep Learning Techniques on SMS Spam Filtering

The Impact of Deep Learning Techniques on SMS Spam Filtering

Organization, Bot, or Human: Towards an Efficient Twitter User Classification

Recurrent Neural Networks (RNNs): Architectures, Training Tricks, and Introduction to Influential Research

Contact Info

Product

Resources

About