Deep Temporal Analysis of Twitter Bots

Automated accounts which are otherwise known as bots are rampant in most of the popular online social networks. Similar to email spam, these social media bots are used for spreading information with the goal of propaganda or advertisements for profit. Due to the impact they pose on influencing the user communities, understanding the bot behaviour is important. In this paper, we employ deep neural network analysis on temporal data of bot accounts and have identified the role of temporal activity in bot detection. The bidirectional LSTM network is used for studying the temporal patterns of Twitter bots and its behavioural pattern. The ability of the model to distinguish the tweeting rate and frequency of bot accounts from the genuine accounts has led to a good classification rate.

[1]  Hossein Hamooni,et al.  DeBot: Twitter Bot Detection via Warped Correlation , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[2]  Roberto Di Pietro,et al.  The Paradigm-Shift of Social Spambots: Evidence, Theories, and Tools for the Arms Race , 2017, WWW.

[3]  Max Nanis,et al.  Socialbots: voices from the fronts , 2012, INTR.

[4]  Julinda Stefa,et al.  Bot and Gender Detection of Twitter Accounts Using Distortion and LSA , 2019, CLEF.

[5]  Emilio Ferrara,et al.  Deep Neural Networks for Bot Detection , 2018, Inf. Sci..

[6]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[7]  Filippo Menczer,et al.  The rise of social bots , 2014, Commun. ACM.

[8]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[9]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[10]  K. P. Soman,et al.  LSTM Based Paraphrase Identification Using Combined Word Embedding Features , 2019, Advances in Intelligent Systems and Computing.

[11]  Hossein Hamooni,et al.  Identifying Correlated Bots in Twitter , 2016, SocInfo.

[12]  Hossein Hamooni,et al.  On-Demand Bot Detection and Archival System , 2017, WWW.

[13]  K. R. Bindu,et al.  A comprehensive study of text classification algorithms , 2017, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[14]  Hossein Hamooni,et al.  Temporal Patterns in Bot Activities , 2017, WWW.

[15]  Emilio Ferrara,et al.  Social Bots Distort the 2016 US Presidential Election Online Discussion , 2016, First Monday.

[16]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[17]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

[18]  Filippo Menczer,et al.  Arming the public with artificial intelligence to counter social bots , 2019, Human Behavior and Emerging Technologies.

[19]  Robert Gorwa,et al.  Unpacking the Social Media Bot: A Typology to Guide Research and Policy , 2018, Policy & Internet.

[20]  P. Metaxas,et al.  Social Media and the Elections , 2012, Science.

[21]  Filippo Menczer,et al.  Online Human-Bot Interactions: Detection, Estimation, and Characterization , 2017, ICWSM.