2018 26th Telecommunications Forum (TELFOR) 2018
DOI: 10.1109/telfor.2018.8611916
|View full text |Cite
|
Sign up to set email alerts
|

Convolutional Neural Network Based SMS Spam Detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
15
0
1

Year Published

2019
2019
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 34 publications
(18 citation statements)
references
References 11 publications
0
15
0
1
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%
See 2 more Smart Citations
“…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%
See 1 more Smart Citation
“…Of late, researchers have started to use deep neural networks such as CNN (Popovac et al, 2018), and LSTM model (Barushka & Hajek, 2018;Jain et al, 2019) features and 200 LSTM nodes, their model achieved an accuracy of 99.01%. They also used three different word embedding techniques: i) Word2Vec, ii) WordNet, and iii) ConcepNet.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Traditionally, convolutional neural network has been utilized for problems related to classifying image. The paper by Milivoje et al [7] in 2018 ran counter to this idea by using CNN for classifying SMS spam messages. Crucial step in their work was preprocessing the data by removing stop words, tokenization, reducing text to lower case where they are working on 'SMS Spam Collection V.1' dataset.…”
Section: Application Of Detecting Spam In Smsmentioning
confidence: 99%