Machine Learning based Spam E-Mail Detection

Sharma, Priti; Bhardwaj, Uma

doi:10.22266/ijies2018.0630.01

Cited by 23 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In six datasets, most emails in Enron 1-3 are legitimate, whereas most emails in Enron 4-6 is spam. This dataset consists of 30,041 electronic messages [17].…”

Section: A Datasetsmentioning

confidence: 99%

E-Mail Spam Filtering Through Feature Selection Using Enriched Firefly Optimization Algorithm

Poonkodi¹

2021

TURCOMAT

View full text Add to dashboard Cite

E-mail is the most common method of communication because due to its ability to obtain, the rapid modification of messages and low cost of distribution. Spam causes traffic issues and bottlenecks that limit the amount of memory and bandwidth, power and computing speed. For data filtering, various approaches exist that automatically detect and suppress these indefensible messages. A methodology based on Sine- Cosine Algorithm (SCA) introduced which address the problem of space and time complexities are increased in E-Mail spam detection. In this method, WordNet optimized semantic ontology applies different methods based on semantics and similarity measures to reduce the large number of extracted textual features. This paper proposed the Enriched Firefly Optimization Algorithm (EFOA) method effectively selecting suitable features from an upper dimensional space using the fitness function. Once the best feature space is identified through EFOA, the spam classification is done using ANN. Intially, E-mail spam dataset is preprocessed, then the extracted textual features are Semantic-based reduction and Features weights updated using optimized semantic WordNet. The results obtained showed that the ANN classifier after selection of features using EFOA was able to classify e-mails as spam and non-spam. This EFOA demonstrates that the proposed method has led to a remarkable improvement compared to the SCA methods.

show abstract

“…In six datasets, most emails in Enron 1-3 are legitimate, whereas most emails in Enron 4-6 is spam. This dataset consists of 30,041 electronic messages [17].…”

Section: A Datasetsmentioning

confidence: 99%

E-Mail Spam Filtering Through Feature Selection Using Enriched Firefly Optimization Algorithm

Poonkodi¹

2021

TURCOMAT

View full text Add to dashboard Cite

show abstract

“…Accuracy, Precision, Recall dan kurva ROC-AUC [16]. Accuracy dihitung dengan menggunakan Confusion Matrix pada Tabel 1 dengan membandingkan penjumlahan True Positif (TP) dan True Negatif (TN) dengan keseluruhan data sesuai dengan persamaan (9). Precision mengukur tingkat ketepatan antara informasi yang diminta oleh pengguna dengan jawaban yang diberikan oleh sistem sesuai persamaan (10), sedangkan recall mengukur tingkat keberhasilan sistem untuk menemukan kembali sebuah informasi melalui persamaan (11)…”

Section: Model Evaluasiunclassified

Deteksi Twitter Bot menggunakan Klasifikasi Decision Tree

Kurniawan

2020

sustainable

View full text Add to dashboard Cite

Advance development of social media application has affected to human lifestyle. Everyone can obtain information from social media easyly. Its become easier to communicate each other using social media. Twitter is one of the fastest growing social media application. Deliver good and hoax information from one user to another. Event there are alot of fake account (bot) in Twitter. This objection of this study is to detect Twitter Bot accounts on Twitter social media by using the Decission Tree classification. Experiment results show the accuracy performance of the Decision Tree model reached 88.84% and UC curve by 0.965. Its shows that the Decision Tree classification is excellent in detecting Twitter Bot accounts.

show abstract

“…Walt [2] explains the concept of identifying bots and human team member Jan and the idea is considering supervised learni words for detecting spam messages in the report on the current trend topic on the internet [3]. They used Filtering [4][5] used for identifying accounts which are in the blacklist and comparing them with the curr existing list of items.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Walt [2] explains the concept of identifying bots and human-managed accounts individually with his team member Jan and the idea is considering supervised learning for text classification using the bag of words for detecting spam messages in the report on the current trend topic on the internet [3]. They used Filtering [4][5] used for identifying accounts which are in the blacklist and comparing them with the curr Yongjun [6] Explains about their research regarding the content matching in the different social platforms related to the same user.…”

Section: Text Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approach for User Accounts Identification with Unwanted Information and data

Kumar

Sairam²

2018

IJMLNCE

View full text Add to dashboard Cite

Machine Learning used for many real-time issues in many organizations and the purpose of social media analytics machine learning models are used most prominently and to identify the genuine accounts and the information in the social media we are here with a new pattern of identification. In this pattern of the model, we are proposing some words which are hidden to identify the accounts with fake data and the some of the steps we are proposing will help to identify the fake and unwanted accounts in Facebook in an efficient manner. Clustering in machine learning will be used, and before that, we are proposing a suitable architecture and the process flow which can identify the fake and suspicious accounts in the social media. This article will be on machine learning implementations and will be working on OSN (online social networks). Our work will be more on Facebook which is maintaining more amount of accounts and identifying which are overruling the rules on privacy and protection of the user content. Machine learning supervised models will be used for text classification, and CNN of unsupervised learning performs the image classification, and the explanation will be given in the implementation phase. There are large numbers of algorithms we can consider for machine learning implementations in the social networking and here we considered mainly on CNN because of having the feasibility of implementation in different rules and we can eliminate the features we don’t need. Feature extraction is quite simple using CNN.

show abstract

Machine Learning based Spam E-Mail Detection

Cited by 23 publications

References 14 publications

E-Mail Spam Filtering Through Feature Selection Using Enriched Firefly Optimization Algorithm

E-Mail Spam Filtering Through Feature Selection Using Enriched Firefly Optimization Algorithm

Deteksi Twitter Bot menggunakan Klasifikasi Decision Tree

Machine Learning Approach for User Accounts Identification with Unwanted Information and data

Contact Info

Product

Resources

About