The 10 million follower fallacy: audience size does not prove domain-influence on Twitter

Cataldi, Mario; Aufaure, Marie-Aude

doi:10.1007/s10115-014-0773-8

Cited by 26 publications

(16 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our results show that both the standard Argumentum Ad Populum and the Group-Ad Populum fallacies, despite their wide use, do not cause any improvement with respect to the neutral condition, thus confirming previous results on the inefficacy of recommendations based on the mere "appeal to the majority" [14,15], but in contrast to other relevant literature [16][17][18][19]). Finally, we found that negative framing, combined with visual accent, is effective in improving the number of clicks on recommended news, consistently with our expectations.…”

Section: Introductionsupporting

confidence: 89%

When Personalization Is Not an Option: An In-The-Wild Study on Persuasive News Recommendation

et al. 2019

View full text Add to dashboard Cite

Aiming at granting wide access to their contents, online information providers often choose not to have registered users, and therefore must give up personalization. In this paper, we focus on the case of non-personalized news recommender systems, and explore persuasive techniques that can, nonetheless, be used to enhance recommendation presentation, with the aim of capturing the user’s interest on suggested items leveraging the way news is perceived. We present the results of two evaluations “in the wild”, carried out in the context of a real online magazine and based on data from 16,134 and 20,933 user sessions, respectively, where we empirically assessed the effectiveness of persuasion strategies which exploit logical fallacies and other techniques. Logical fallacies are inferential schemes known since antiquity that, even if formally invalid, appear as plausible and are therefore psychologically persuasive. In particular, our evaluations allowed us to compare three persuasive scenarios based on the Argumentum Ad Populum fallacy, on a modified version of the Argumentum ad Populum fallacy (Group-Ad Populum), and on no fallacy (neutral condition), respectively. Moreover, we studied the effects of the Accent Fallacy (in its visual variant), and of positive vs. negative Framing.

show abstract

Section: Introductionsupporting

confidence: 89%

When Personalization Is Not an Option: An In-The-Wild Study on Persuasive News Recommendation

et al. 2019

View full text Add to dashboard Cite

show abstract

“…These results are neglecting the majority of tweets and can mislead a topic-based user influence, as 4 out of 5 of her tweets are not considered for measuring her influence. Cataldi and Aufaure (2015) and Bingol et al (2016) estimated user influence for topics based on PageRank. For that purpose they build a topic information exchange graph to take the information diffusion and degree of information shared into account for user influence estimation.…”

Section: Topic-based Influencementioning

confidence: 99%

“…Montangero and Furini (2015) compared their method to the number of followers of the users of interest. Cataldi and Aufaure (2015) used opinions from experts to evaluate their proposed influence measure. Lastly, Katsimpras et al (2015) used PageRank scores for as their evaluation measure.…”

Section: User Influence Measurement On the Identified Topics From Thementioning

confidence: 99%

Collaborative topic regression for predicting topic-based social influence

et al. 2019

View full text Add to dashboard Cite

The rapid growth of social networks and their strong presence in our lives have attracted many researchers in social networks analysis. Users of social networks spread their opinions, get involved in discussions, and consequently, influence each other. However, the level of influence of different users is not the same. It varies not only among users, but also for one user across different topics. The structure of social networks and user-generated content can reveal immense information about users and their topic-based influence. Although many studies have considered measuring global user influence, measuring and estimating topic-based user influence has been under-explored. In this paper, we propose a collaborative topic-based social influence model that incorporates both network structure and user-generated content for topic-based influence measurement and prediction. We predict topic-based user influence on unobserved topics, based on observed topic-based user influence through their generated contents and activities in social networks. We perform experimental analysis on Twitter data, and show that our model outperforms state-of-the-art approaches on recall, accuracy, precision, and F-score for predicting topic-based user influence.

show abstract

“…These results are neglecting the majority of tweets and can mislead a topic-based user influence, as 4 out of 5 of her tweets are not considered for measuring her influence. Cataldi and Aufaure (2014) estimated Twitter user influence for topics of conversations based on PageRank. For that purpose they build a topic information exchange graph to take the information diffusion and degree of information shared into account for user influence estimation.…”

Section: Related Workmentioning

confidence: 99%

Topic-based Social Influence Measurement for Social Networks

Hamzehei

Jiang²,

Koutra

et al. 2017

AJIS

View full text Add to dashboard Cite

Social science studies have acknowledged that the social influence of individuals is not identical. Social networks structure and shared text can reveal immense information about users, their interests, and topic-based influence. Although some studies have considered measuring user influence, less has been on measuring and estimating topic-based user influence. In this paper, we propose an approach that incorporates network structure, usergenerated content for topic-based influence measurement, and user's interactions in the network. We perform experimental analysis on Twitter data and show that our proposed approach can effectively measure topic-based user influence.

show abstract

The 10 million follower fallacy: audience size does not prove domain-influence on Twitter

Cited by 26 publications

References 42 publications

When Personalization Is Not an Option: An In-The-Wild Study on Persuasive News Recommendation

When Personalization Is Not an Option: An In-The-Wild Study on Persuasive News Recommendation

Collaborative topic regression for predicting topic-based social influence

Topic-based Social Influence Measurement for Social Networks

Contact Info

Product

Resources

About