Predicting Rising Follower Counts on Twitter Using Profile Information

Abstract

When evaluating the cause of one's popularity on Twitter, one thing is considered to be the main driver: Many tweets. There is debate about the kind of tweet one should publish, but little beyond tweets. Of particular interest is the information provided by each Twitter user's profile page. One of the features are the given names on those profiles. Studies on psychology and economics identified correlations of the first name to, e.g., one's school marks or chances of getting a job interview in the US. Therefore, we are interested in the influence of those profile information on the follower count. We addressed this question by analyzing the profiles of about 6 Million Twitter users. All profiles are separated into three groups: Users that have a first name, English words, or neither of both in their name field. The assumption is that names and words influence the discoverability of a user and subsequently his/her follower count. We propose a classifier that labels users who will increase their follower count within a month by applying different models based on the user's group. The classifiers are evaluated with the area under the receiver operator curve score and achieves a score above 0.800.

Twitter interaction between audiences and influencers. Sentiment, polarity, and communicative behaviour analysis methodology

“…Contrary to the study by Mueller and Stumme (2017), the results of our research show that the account with the highest number of followers is not the one with the highest number of tweets and retweets, partly coinciding with the findings of Fernández-Muñoz and García-Guardia (2016) on the dissassociation between interactivity and number of followers. Nevertheless, the tendency of teenagers and young adults to click on Like instead of posting comments (Edelmann, 2017;Bossen;Kottasz, 2020) might explain our findings that retweets are not associated with more popularity, as suggested by Wallner, Kirigslein and Drachen (2019), and Jain and Sinha (2020) It can also be observed that teenagers and young people (the main targets of the accounts studied) set clearly defined trends, as the activity generated by one of the influencers studied (@IbaiLlanos) is exponentially greater than the rest.…”

“…We believe that these low registers are not a mere coincidence. Instead, we consider this to be a strategy of the figures under study, the purpose of which is to engage a larger number of followers by expressing their opinions (Mueller;Stumme, 2017). Similarly, the connection or relation between the user and the content, described in the concept of parasocial interaction (Stever; Lawson, 2013; Dibble; Hartmann; Rosaen, 2015; Kim; Song, 2016, among others), can lead to responses that mimic the influencer's comments (Sailunaz;Alhajj, 2019).…”

The Impact of Viral Posts on Visibility and Behavior of Professionals: A Longitudinal Study of Scientists on Twitter

“…We studied virality's impact(s) on behavioral changes. We focused on behaviors related to building scholarly reputation as identified by prior research: tweeting frequency, sentiment, objectivity, and engaging professionally with other scholars (i.e., posting tweets that are aligned with the posters area of expertise) (Mueller and Stumme 2017;Schnitzler et al 2016). We also examined if viral users, after the first virality, posted tweets that were more similar to the viral tweet, presumably, as a way to re-create the cascading phenomenon, and if they tweeted on more (or less) diverse topics after the viral events, than before.…”

Modeling Influence with Semantics in Social Networks

“…Finally, the authors in [122] propose a machine learning methodology for investigating the impact of profile information towards the increase of Twitter accounts' popularity, in terms of their followers' count. Based on the assumption that given names and English words affect the discoverability, profiles were analyzed and categorized into three groups according to the lexical content of the accounts' name: i) having a first name, ii) containing English words, or iii) neither of both.…”