Enhanced Twitter bot detection using ensemble machine learning

Shukla, Hrushikesh; Jagtap, Nakshatra; Patil, Balaji

doi:10.1109/icict50816.2021.9358734

“…To validate our approach, as shown in Table 5, we used the whole dataset and compared the performance measures' AUC, precision, recall, and F1 score for the CVAE features subset with six features using RF with a recent benchmark study that used the same dataset and classifier (Shukla et al, 2021). WoE encoding was used to recognize unique values in nominal feature attributes.…”

Section: Discussionmentioning

confidence: 99%

“…A recent study by Shukla et al (2021) evaluated profile metadata features using an ensemble machine-learning algorithm. The proposed work used weight-of-evidence (WoE) encoding profile features using three ensemble learning algorithms: RF, AdaBoost, and artificial NNs.…”

Section: Bot Detection Features In Twittermentioning

confidence: 99%

See 1 more Smart Citation

Hybrid feature selection approach to identify optimal features of profile metadata to detect social bots in Twitter

Alothali

¹

,

Hayawi

²

,

Alashwal

³

2021

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

The last few years have revealed that social bots in social networks have become more sophisticated in design as they adapt their features to avoid detection systems. The deceptive nature of bots to mimic human users is due to the advancement of artificial intelligence and chatbots, where these bots learn and adjust very quickly. Therefore, finding the optimal features needed to detect them is an area for further investigation. In this paper, we propose a hybrid feature selection (FS) method to evaluate profile metadata features to find these optimal features, which are evaluated using random forest, naïve Bayes, support vector machines, and neural networks. We found that the cross-validation attribute evaluation performance was the best when compared to other FS methods. Our results show that the random forest classifier with six optimal features achieved the best score of 94.3% for the area under the curve. The results maintained overall 89% accuracy, 83.8% precision, and 83.3% recall for the bot class. We found that using four features: favorites_count, verified, statuses_count, and average_tweets_per_day, achieves good performance metrics for bot detection (84.1% precision, 81.2% recall).

show abstract

“…Different types of bots target various audiences; for example, spam bots for spreading spam, fake follower for increasing followers of a particular account, COVID, or political bots for spreading conspiracy. Alom, Carminati and Ferrari (2018) and Shukla, Jagtap and Patil (2021) tried to detect spam bots on Twitter platform. Alom, Carminati and Ferrari (2018) have used metadata and graph-based features from the 42K dataset collected by a Social Honeypot.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Algorithms for Detecting and Analyzing Social Bots Using a Novel Dataset

Jalal

¹

,

Ghafoor²

2022

ARO

1

0

View full text Add to dashboard Cite

Social media is internet-based technology and an electronic form of communication that facilitates sharing of ideas, documents, and personal information. Twitter is a microblogging platform and is the most effective social service for posting microblogs and likings, commenting, sharing, and communicating with others. The problem we are shedding light on in this paper is the misuse of bots on Twitter. The purpose of bots is to automate specific repetitive tasks instead of human interaction. However, bots are misused to influence people’s minds by spreading rumors and conspiracy related to controversial topics. In this paper, we initiate a new benchmark created on a 1.5M Twitter profile. We train different supervised machine learning on our benchmark to detect bots on Twitter. In addition to increasing benchmark scalability, various autofeature selections are utilized to identify the most influential features and remove the less influential ones. Furthermore, over-under-sampling is applied to reduce the imbalance effect on the benchmark. Finally, our benchmark compared with other stateof-the-art benchmarks and achieved a 6% higher area under the curve than other datasets in the case of generalization, improving the model performance by at least 2% by applying over-/undersampling.

show abstract

“…They used different ML models; the random forest (RF) achieved the best result compared to other models. Furthermore, Shukla, Jagtap and Patil (2021) and Shevtsov, et al (2021) focused on detecting bots that spread rumors. Khanday, Khan and Rabani (2021) have used Tweeter API to collect tweets related to the COVID19 outbreak.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Algorithms for Detecting and Analyzing Social Bots Using a Novel Dataset

Jalal

¹

,

Ghafoor²

2022

ARO

1

0

View full text Add to dashboard Cite

Social media is internet-based technology and an electronic form of communication that facilitates sharing of ideas, documents, and personal information. Twitter is a microblogging platform and is the most effective social service for posting microblogs and likings, commenting, sharing, and communicating with others. The problem we are shedding light on in this paper is the misuse of bots on Twitter. The purpose of bots is to automate specific repetitive tasks instead of human interaction. However, bots are misused to influence people’s minds by spreading rumors and conspiracy related to controversial topics. In this paper, we initiate a new benchmark created on a 1.5M Twitter profile. We train different supervised machine learning on our benchmark to detect bots on Twitter. In addition to increasing benchmark scalability, various autofeature selections are utilized to identify the most influential features and remove the less influential ones. Furthermore, over-under-sampling is applied to reduce the imbalance effect on the benchmark. Finally, our benchmark compared with other stateof-the-art benchmarks and achieved a 6% higher area under the curve than other datasets in the case of generalization, improving the model performance by at least 2% by applying over-/undersampling.

show abstract

Enhanced Twitter bot detection using ensemble machine learning

Cited by 27 publications

References 14 publications

Hybrid feature selection approach to identify optimal features of profile metadata to detect social bots in Twitter

Hybrid feature selection approach to identify optimal features of profile metadata to detect social bots in Twitter

Machine Learning Algorithms for Detecting and Analyzing Social Bots Using a Novel Dataset

Machine Learning Algorithms for Detecting and Analyzing Social Bots Using a Novel Dataset

Contact Info

Product

Resources

About