CodeScan: A Supervised Machine Learning Approach to Open Source Code Bot Detection

Gaurav, Vipul; Singh, Shresth; Srivastava, Avikant; Shidnal, Sushila

doi:10.1007/978-981-16-2008-9_37

Cited by 1 publication

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To categorize tweets as bot tweets or not, a neural network ensemble of CNN and LSTM models with BERT embedding was developed by Kumar et al [26] which is based on the tweets' textual content. Gaurav et al [27] pinpointed account patterns types using machine learning mechanisms and provides intelligent clues that may be utilized as a robustness gauge for several systems. Several machine learning approaches for detecting malicious users have been suggested on Praveena [28] work based on glow worm optimization technique to in order to deal with a small set of features.…”

Section: Related Workmentioning

confidence: 99%

Hybrid-MELAu: A Hybrid Mixing Engineered Linguistic Features Based on Autoencoder for Social Bot Detection.

Hamida

Refouf

Drif

et al. 2022

IJCAI

View full text Add to dashboard Cite

Social bots are defined as computer algorithms that generate massive amounts of obnoxious or meaningful information. Most bot detection methods leverage multitudinous characteristics, from network features, temporal dynamics features, activities features, and sentiment features. However, there has been fairly lower work exploring lexicon measurement and linguistic indicators to detect bots. The main purpose of this research is to recognize the social bots through their writing style. Thus, we carried out an exploratory study on the effectiveness of only a set of linguistic features (17 features) exploitable for bot detection, without the need to resort to other types of features. And we develop a novel framework in a hybrid fashion of Mixing Engineered Linguistic features based on Autoencoders (Hybrid-MELAu). The semisupervised Hybrid-MELAu framework is composed of two essential constituents: the features learner and the predictors. We establish the features learner innovated on two powerful structures: a) the first is a Deep dense Autoencoder fed by the Lexical and the Syntactic content (DALS) that represents the high order lexical and syntactic features in latent space, b) the second one is a Glove-BiLSTM autoencoder, which sculpts the semantic features; subsequently, we generate elite elements from the pre-trained encoder part from each latent space with transfer learning. We consider a sample of 1 Million from Cresci datasets to conduct our linguistic analysis comparison between the writing style of humans and bots. With this dataset, we observe that the bot's textual lexical diversity median is greater than the human one and the syntactic analysis based on speech-tagging shows a creative behavior in human writing style. Finally, we test the model's robustness on several public dataset (celebrity, pronbots-2019, and political bots). The proposed framework achieves a good accuracy of 92.22%. Overall, the results shown in this paper, and the related discussion, argue that it is possible to discern the differences between humans' and bots' writing styles based on an efficient linguistic deep framework.Povzetek: V prispevku je opisana metoda za detekcijo pogovornih asistentov (botov) na osnovi jezkovnega stila.

show abstract

Section: Related Workmentioning

confidence: 99%