Online Social Media platforms, such as Facebook and Twitter, enable all users, independently of their characteristics, to freely generate and consume huge amounts of data. While this data is being exploited by individuals and organisations to gain competitive advantage, a substantial amount of data is being generated by spam or fake users. One in every 200 social media messages and one in every 21 tweets is estimated to be spam. The rapid growth in the volume of global spam is expected to compromise research works that use social media data, thereby questioning data credibility. Motivated by the need to identify and filter out spam contents in social media data, this study presents a novel approach for distinguishing spam vs. non-spam social media posts and offers more insight into the behaviour of spam users on Twitter. The approach proposes an optimised set of features independent of historical tweets, which are only available for a short time on Twitter. We take into account features related to the users of Twitter, their accounts and their pairwise engagement with each other. We experimentally demonstrate the efficacy and robustness of our approach and compare it to a typical feature set for spam detection in the literature, achieving a significant improvement on performance. In contrast to prior research findings, we observe that an average automated spam account posted at least 12 tweets per day at well defined periods. Our method is suitable for real-time deployment in a social media data collection pipeline as an initial preprocessing strategy to improve the validity of research data.
The rise in the number of automated or bot accounts on Twitter engaging in manipulative behaviour is of great concern to studies using social media as a primary data source. Many strategies have been proposed and implemented, however, the sophistication and rate of deployment of bot accounts is increasing rapidly. This impedes and limits the capabilities of detecting bot strategies. Various features broadly related to account profiles, tweet content, network and temporal patterns have been utilised in detection systems. Tweet content has been proven instrumental in this process, but limited to the terms and entities occurring. Given a set of tweets with no obvious pattern, can we distinguish contents produced by social bots from those of humans? What constitutes engagement on Twitter and how can we measure the intensity of engagement among Twitter users? Can we distinguish between bot and human accounts based on engagement intensity? These are important questions whose answer will improve how detection systems operate to combat malicious activities by effectively distinguishing between human and social bot accounts on Twitter. This study attempts to answer these questions by analysing the engagement intensity and lexical richness of tweets produced by human and social bot accounts using large, diverse datasets. Our results show a clear margin between the two classes in terms of engagement intensity and lexical richness. We found that it is extremely rare for a social bot to engage meaningfully with other users and that lexical features significantly improve the performance of classifying both account types. These are important dimensions to explore toward improving the effectiveness of detection systems in combating the menace of social bot accounts on Twitter.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.