Who leads the conversation? Influential Twitter users during a niche sporting event

Fans of niche sports generally find minimal content in mainstream media due to their limited audience. Instead, social media offers them the opportunity to follow these specific sports. The dynamics behind digital media are based on individual participation, hence some prominent users lead the social conversation thanks to their capacity to influence. However, the complexity of the concept of influence and the existence of multiple parameters for its measurement make it difficult to identify these key users. Our research proposes a measure of the influence on Twitter based on variables derived from the platform (number of tweets, number of retweets, and number of followers) and from the Social Network Analysis (outdegree, indegree, and PageRank). The Analytic Hierarchy Process was used to assign a weight to each variable. This measure of influence was applied to the conversation generated on Twitter around a niche sporting event: the 2018 UCI Track Cycling World Championships. From a 19 701-tweet corpus, we identified the 25 most influential users. The results indicate that the organisers and the participating cyclists played a relevant role in the Twitter conversation. In addition, the geographic distribution of these influential users reflects the cultural dependence of niche sports.

A quick GRASP-based method for influence maximization in social networks

The evolution and spread of social networks have attracted the interest of the scientific community in the last few years. Specifically, several new interesting problems, which are hard to solve, have arisen in the context of viral marketing, disease analysis, and influence analysis, among others. Companies and researchers try to find the elements that maximize profit, stop pandemics, etc. This family of problems is collected under the term Social Network Influence Maximization problem (SNIMP), whose goal is to find the most influential users (commonly known as seeds) in a social network, simulating an influence diffusion model. SNIMP is known to be an $$\mathcal {NP}$$ NP -hard problem and, therefore, an exact algorithm is not suitable for solving it optimally in reasonable computing time. The main drawback of this optimization problem lies on the computational effort required to evaluate a solution. Since each node is infected with a certain probability, the objective function value must be calculated through a Monte Carlo simulation, resulting in a computationally complex process. The current proposal tries to overcome this limitation by considering a metaheuristic algorithm based on the Greedy Randomized Adaptive Search Procedure (GRASP) framework to design a quick solution procedure for the SNIMP. Our method consists of two distinct stages: construction and local search. The former is based on static features of the network, which notably increases its efficiency since it does not require to perform any simulation during construction. The latter involves a local search based on an intelligent neighborhood exploration strategy to find the most influential users based on swap moves, also aiming for an efficient processing. Experiments performed on 7 well-known social network datasets with 5 different seed set sizes confirm that the proposed algorithm is able to provide competitive results in terms of quality and computing time when comparing it with the best algorithms found in the state of the art.

Antivaccine Movement and COVID-19 Negationism: A Content Analysis of Spanish-Written Messages on Twitter

During the COVID-19 pandemic, different conspiracies have risen, with the most dangerous being those focusing on vaccines. Today, there exists a social media movement focused on destroying the credibility of vaccines and trying to convince people to ignore the advice of governments and health organizations on vaccination. Our aim was to analyze a COVID-19 antivaccination message campaign on Twitter that uses Spanish as the main language, to find the key elements in their communication strategy. Twitter data were retrieved from 14 to 28 December using NodeXL software. We analyzed tweets in Spanish, focusing on influential users, most influential tweets, and content analysis of tweets. The results revealed ordinary citizens who ‘offer the truth’ as the most important profile in this network. The content analysis showed antivaccine tweets (31.05%) as the most frequent. The analysis of anti-COVID19 tweets showed that attacks against vaccine safety were the most important (79.87%) but we detected a new kind of message presenting the vaccine as a means of manipulating the human genetic code (8.1%). We concluded that the antivaccine movement and its tenets have great influence in the COVID-19 negationist movement. We observed a new topic in COVID-19 vaccine hoaxes that must be considered in our fight against misinformation.

On Modeling Influence Maximization in Social Activity Networks under General Settings

Finding the set of most influential users in online social networks (OSNs) to trigger the largest influence cascade is meaningful, e.g., companies may leverage the “word-of-mouth” effect to trigger a large cascade of purchases by offering free samples/discounts to those most influential users. This task is usually modeled as an influence maximization problem, and it has been widely studied in the past decade. However, considering that users in OSNs may participate in various online activities, e.g., joining discussion groups and commenting on same pages or products, influence diffusion through online activities becomes even more significant. In this article, we study the impact of online activities by formulating social-activity networks which contain both users and online activities, and thus induce two types of weighted edges, i.e., edges between users and edges between users and activities. To address the computation challenge, we define an influence centrality via random walks, and use the Monte Carlo framework to efficiently estimate the centrality. Furthermore, we develop a greedy-based algorithm with novel optimizations to find the most influential users for node recommendation. Experiments on real-world datasets show that our approach is very computationally efficient under different influence models, and also achieves larger influence spread by considering online activities.

Cross-site Prediction on Social Influence for Cold-start Users in Online Social Networks

Online social networks (OSNs) have become a commodity in our daily life. As an important concept in sociology and viral marketing, the study of social influence has received a lot of attentions in academia. Most of the existing proposals work well on dominant OSNs, such as Twitter, since these sites are mature and many users have generated a large amount of data for the calculation of social influence. Unfortunately, cold-start users on emerging OSNs generate much less activity data, which makes it challenging to identify potential influential users among them. In this work, we propose a practical solution to predict whether a cold-start user will become an influential user on an emerging OSN, by opportunistically leveraging the user’s information on dominant OSNs. A supervised machine learning-based approach is adopted, transferring the knowledge of both the descriptive information and dynamic activities on dominant OSNs. Descriptive features are extracted from the public data on a user’s homepage. In particular, to extract useful information from the fine-grained dynamic activities that cannot be represented by the statistical indices, we use deep learning technologies to deal with the sequential activity data. Using the real data of millions of users collected from Twitter (a dominant OSN) and Medium (an emerging OSN), we evaluate the performance of our proposed framework to predict prospective influential users. Our system achieves a high prediction performance based on different social influence definitions.

Predicting Influential Users in Online Social Network Groups

The widespread adoption of Online Social Networks (OSNs), the ever-increasing amount of information produced by their users, and the corresponding capacity to influence markets, politics, and society, have led both industrial and academic researchers to focus on how such systems could be influenced . While previous work has mainly focused on measuring current influential users, contents, or pages on the overall OSNs, the problem of predicting influencers in OSNs has remained relatively unexplored from a research perspective. Indeed, one of the main characteristics of OSNs is the ability of users to create different groups types, as well as to join groups defined by other users, in order to share information and opinions. In this article, we formulate the Influencers Prediction problem in the context of groups created in OSNs, and we define a general framework and an effective methodology to predict which users will be able to influence the behavior of the other ones in a future time period, based on historical interactions that occurred within the group. Our contribution, while rooted in solid rationale and established analytical tools, is also supported by an extensive experimental campaign. We investigate the accuracy of the predictions collecting data concerning the interactions among about 800,000 users from 18 Facebook groups belonging to different categories (i.e., News, Education, Sport, Entertainment, and Work). The achieved results show the quality and viability of our approach. For instance, we are able to predict, on average, for each group, around a third of what an ex-post analysis will show being the 10 most influential members of that group. While our contribution is interesting on its own and—to the best of our knowledge—unique, it is worth noticing that it also paves the way for further research in this field.

Profiling the Users of High Influence on Social Media in the Context of Public Events

The highly influential users on social media platforms may lead the public opinion about public events and have positive or negative effects on the later evolution of events. Identifying highly influential users on social media is of great significance for the management of public opinion in the context of public events. In this study, the highly influential users of social media are divided into three types (i.e., topic initiator, opinion leader, and opinion reverser). A method of profiling highly influential users is proposed based on topic consistency and emotional support. The event of “Jiankui He Editing the Infants' Genes” was investigated. The three types of users were identified, and their opinion differences and dynamic evolution were revealed. The comprehensive profiles of highly influential users were constructed. The findings can help emergency management departments master the focus of attention and emotional attitudes of the key users and provide the method and data support for opinion management and decision-making of public events.

Influence Without Metrics: Analyzing the Impact of Far-Right Users in an Online Discussion Forum

The study presented in this article explores the processes through which influence takes shape in eclectic online forums with few vanity metrics. Using a dataset of 7.5 million posts in the large Swedish online discussion forum Flashback, it explores who becomes influential, their strategies for appealing to the community, and others’ support of them. While it has been known that Flashback hosts far-right users and content, the current study shows that these sentiments are not fringe or obscure, but instead seemingly widely supported and influential in the forum. It illustrates that the influential users—those who are supported and acknowledged by others as important—exclusively and continuously expressed far-right ideas and displayed an embeddedness within the far-right, as well as in the forum’s culture. The study finds that despite few visible markers, many users learned to recognize influential users and their far-right content as worthy of support. In the absence of built-in functions, some users engaged in manual “liking” and “sharing” of influential users’ content via their replies, acknowledging it as a way to legitimize them. At the same time, the analysis showcased how a lack of vanity metrics countered potential echo chamber effects in the forum as disliked users—advocating progressive gender and immigration ideas—were unintentionally amplified by those who attempted to silence them. The article also discusses the role of Flashback as a platform in the proliferation of hate.