Skip to main content
Log in

Fake account detection in twitter using logistic regression with particle swarm optimization

  • Application of soft computing
  • Published:
Soft Computing Aims and scope Submit manuscript


Online social networks (OSNs) have incredibly grown over the past decades. People connect with their friends, family members, new people and share their views or fun artifact with them through OSNs such as Facebook, Twitter, Instagram, Telegram, etc. However, the global and easy connection have also attracted many fake users to lure the genuine users to fulfill their own malicious intention. In the proposed work, the fake accounts (fake followers) detection in Twitter by selecting the relevant features that define the profile’s characteristics users has been studied. Here, logistic regression integrated with the particle swarm optimization (PSO) have been proposed to effectively classify an account as genuine or fake. In addition, opposition-based initialization is combined with PSO to start the exploration of the search space with a good set of solutions. Feature selection techniques, namely information gain, correlation, and minimum redundancy maximum relevance, were also applied to select the informative subset of features from the original feature space. The conducted experiments demonstrate that the proposed model attains better performance compare to the competitive state-of-the-arts in most of the cases.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others





  • Adikari S, Dutta K (2014) Identifying fake profiles in LinkedIn, PACIS, p 278

  • Alias N, Sabdan MS, Aziz KA, Mohammed M, Hamidon IS, Jomhari N (2013) Research trends and issues in the studies of Twitter: a content analysis of publications in selected journals (2007–2012). Proc Soc Behav Sci 103:773–780

    Article  Google Scholar 

  • Alsaleh M, Alarifi A, Al-Salman AM, Alfayez M, Almuhaysin A (2014) Tsd: detecting sybil accounts in twitter. In: 13th International conference on machine learning and applications, pp 463–469

  • Arora A, Bansal S, Kandpal C, Aswani R, Dwivedi Y (2019) Measuring social media influencer index-insights from facebook, Twitter and Instagram. J Retail Consum Serv 49(C):86–101

    Article  Google Scholar 

  • Atodiresei CS, Tanaselea Alexandru IA (2018) Identifying fake news and fake users on Twitter. Proc Comput Sci 126:451–461

    Article  Google Scholar 

  • Bala Anand M, Karthikeyan N, Karthik S, Varatharajan R, Manogaran G, Sivaparthipan CB (2019) An enhanced graph-based semi-supervised learning algorithm to detect fake users on Twitter. J Supercomput 75(9):6085–6105

    Article  Google Scholar 

  • Bansal H, Misra M (2016) Sybil detection in online social networks (OSNS). In: IEEE 6th international conference on advanced computing (IACC), pp 569–576

  • Benevenuto F, Magno G, Rodrigues T, Almeida V (2010) Detecting spammers on twitter, collaboration, electronic messaging, anti-abuse and spam conference (CEAS), p 12

  • Cao Jian F, Qiang LQ, Dong G (2017) Discovering hidden suspicious accounts in online social networks. Inf Sci 394:123–140

    Google Scholar 

  • Cao Q (2014) Understanding and defending against malicious identities in online social networks. Duke University

  • Cao Q, Sirivianos M, Yang X, Pregueiro T (2012) Aiding the detection of fake accounts in large scale social online services. In: Proceedings of the 9th USENIX conference on networked systems design and implementation, pp 15–15

  • Devakunchari R, Valliyammai C (2018) Fake profile detection techniques in large-scale online social networks: a comprehensive review. Comput Electric Eng 65:165–177

    Article  Google Scholar 

  • Dhal KG, Ray S, Das A, Das S (2019) A survey on nature-inspired optimization algorithms and their application in image enhancement domain. Arch Comput Methods Eng 26:1607–1638

    Article  MathSciNet  Google Scholar 

  • Dickerson JP, Kagan V, Subrahmanian VS (2014) Using sentiment to detect bots on twitter: are humans more opinionated than bots? In: Proceedings of the 2014 IEEE/ACM international conference on advances in social networks analysis and mining, pp 620–627

  • Di P, Roberto C, Stefano P, Marinella S, Angelo TM (2013) Fake accounts detection on Twitter

  • El Azab A, Ahmed I, Amira M, Mahmoud MA, Hefny H (2016) Fake account detection in twitter based on minimum weighted feature set. Int Sch Sci Res Innov 10(1):13–18

    Google Scholar 

  • Emilio F, Onur V, Clayton D, Filippo M, Alessandro F (2016) The rise of social bots. Commun ACM 59(7):96–104

    Article  Google Scholar 

  • Gupta A, Kaushal R (2017) Towards detecting fake user accounts in facebook. In: ISEA Asia security and privacy (ISEASP), pp 1–6

  • Gurajala S, White JS, Hudson B, Voter BR, Matthews JN (2016) Profile characteristics of fake Twitter accounts. Big Data Soc 3:2

    Article  Google Scholar 

  • Hall MA (1999) Correlation-based feature selection for machine learning, PhD dissertation

  • Hemeida AM, Alkhalaf S, Mady A, Mahmoud EA, Hussein ME, Eldin AMB (2020) Implementation of nature-inspired optimization algorithms in some data mining tasks. Ain Shams Eng J 11(2):309–318

    Article  Google Scholar 

  • Jiang Y, Li C (2015) mRMR-based feature selection for classification of cotton foreign matter using hyperspectral imaging. Comput Electron Agric 119:191–200

    Article  Google Scholar 

  • Kapoor KK, Tamilmani K, Rana NP, Patil P, Dwivedi YK, Nerur S (2018) Advances in social media research: past, present and future. Inf Syst Front 20:531–558

    Article  Google Scholar 

  • Khalil A, Hajjdiab H, Al-Qirim N (2017) Detecting fake followers in twitter: a machine learning approach. Int J Mach Learn Comput 7:6

    Google Scholar 

  • Kondeti P, Yerramreddy L. P, Pradhan A, Swain G (2021) Fake account detection using machine learning. In: Evolutionary computing and mobile sustainable networks, pp 791–802

  • Kuss DJ, Griffiths MD (2011) Online social networking and addiction—a review of the psychological literature. Int J Environ Res Public Health 8(9):3528–3552

    Article  Google Scholar 

  • Lee K, Caverlee J, Webb S (2010) The social honeypot project: protecting online communities from spammers. In: Proceedings of the 19th international conference on world wide web, pp 1139–1140

  • Martínez Romo J, Araujo L (2013) Detecting malicious tweets in trending topics using a statistical analysis of language. Expert Syst Appl 40:2992–3000

    Article  Google Scholar 

  • Mavrovouniotis M, Li C, Yang S (2017) A survey of swarm intelligence for dynamic optimization: algorithms and applications. Swarm Evol Comput 33:1–17

    Article  Google Scholar 

  • Nandi G (2013) A survey on using data mining techniques for online social network analysis. Int J Comput Sci Issue 10(6):162–167

    Google Scholar 

  • Rahnamayan S, Tizhoosh HR, Salama MMA (2017) A novel population initialization method for accelerating evolutionary algorithms. Comput Math Appl 53(10):1605–1614

    Article  MathSciNet  MATH  Google Scholar 

  • Reddy RN, Kumar N (2012) Automatic detection of fake profiles in online social networks

  • Ruhela A, Amitabha B, Anirban M, Aaditeshwar S (2016) The rich and middle classes on Twitter: are popular users indeed different from regular users? Comput Commun 73:219–228

    Article  Google Scholar 

  • Ryerkerk M, Averill R, Deb K, Goodman E (2019) A survey of evolutionary algorithms using metameric representations. Genet Program Evol Mach 20:441–478

    Article  Google Scholar 

  • Sahoo SR, Gupta BB (2019) Hybrid approach for detection of malicious profiles in Twitter. Comput Electr Eng 76:65–81

    Article  Google Scholar 

  • Sakariyah AK, Badrul AN, Amirrudin K, Dewi VK, Abdul RS (2017) Malicious accounts: dark of the social networks. J Netw Comput Appl 79:41–67

    Article  Google Scholar 

  • Sarmah DK (2019) A survey on the latest development of machine learning in genetic algorithm and particle swarm optimization. Optim Mach Learn Appl 91–112

  • Sharma M, Kaur P (2020) A comprehensive analysis of nature-inspired meta-heuristic techniques for feature selection problem. Arch Comput Methods Eng

  • Stefano C, Di PR, Petrocchi M, Spognardi A, Tesconi M (2015) Fame for sale: efficient detection of fake Twitter followers. Decis Support Syst 80:56–71

    Article  Google Scholar 

  • Stefano C, Di P, Roberto PM, Spognardi A, Tesconi M (2015) Fame for sale: efficient detection of fake Twitter followers. Decis Support Syst 56–71:80

  • Stringhini G, Kruegel C, Vigna G (2010) Detecting spammers on social networks. In: Proceedings of the 26th annual computer security applications conference, pp 1–9

  • Thomas K, McCoy D, Grier C, Kolcz A, Paxson V (2013) Trafficking fraudulent accounts: the role of the underground market in Twitter spam and abuse. Presented as part of the 22nd USENIX security symposium (USENIX Security 13), pp 195–210

  • Venkatesh R, Rout JK, Jena SKM (2017) Account detection based on short URLs in Twitter. In: Proceedings of the international conference on signal, networks, computing, and systems, pp 243–251

  • Wanda P, Jin JH (2020) DeepProfile: finding fake profile in online social network using dynamic CNN. J Inform Secur Appl 52:1–13

    Google Scholar 

  • Wang Y, Makedon FS, Ford JC, Pearlman J (2005) HykGene: a hybrid approach for selecting marker genes for phenotype classification using microarray gene expression data. Bioinformatics 21:1530–1537

    Article  Google Scholar 

  • Xiaoming F, Passarella A, Quercia D, Sala A, Strufe T (2016) Online social networks. Comput Commun 73:163–166

    Article  Google Scholar 

  • Yang C, Harkreader RC, Gu G (2011) Die free or live hard? Empirical evaluation and new design for fighting evolving twitter spammers. In: International workshop on recent advances in intrusion detection, pp 318–337

  • Yardi S, Romero D, Schoenebeck G (2010) Detecting spam in a twitter network. First Monday 15:1

    Google Scholar 

  • Yazan B, Dionysios L, Georgos S, Jorge L, Jose L, Matei R, Konstantin B (2015) Integro: leveraging victim prediction for robust fake account detection in OSNs. NDSS 15:8–11

    Google Scholar 

  • Zachary M, Brian D, Deitrick William H, Wei WAH (2014) Twitter spammer detection using data stream clustering. Inf Sci 260:64–73

    Article  Google Scholar 

  • Zelinka I (2015) A survey on evolutionary algorithms dynamics and its complexity—mutual relations, past, present and future. Swarm Evolut Comput 25:2–14

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Kusum Kumari Bharti.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bharti, K.K., Pandey, S. Fake account detection in twitter using logistic regression with particle swarm optimization. Soft Comput 25, 11333–11345 (2021).

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: