Predicting tie strength with social media

Gilbert, Éric; Karahalios, Karrie

doi:10.1145/1518701.1518736

Cited by 1,065 publications

(854 citation statements)

References 37 publications

Supporting

Mentioning

802

Contrasting

Unclassified

Order By: Relevance

“…Regarding to the relationship intensity, Mark Granovetter introduces a concept called tie strength-strong or weak-to describe the relationship intensity of social ties [7]. Strong ties usually refer to links between family and close friends [8], having extensive interactions [9], while weak ties refer to links between loose acquaintances [10], who often provide access to novel information.…”

Section: Social Tie Analysismentioning

confidence: 99%

Estimating Social Tie Strength for Autonomous D2D Collaborations

Choi¹,

Kang²,

Jung³

et al. 2015

IJFCC

View full text Add to dashboard Cite

7 Abstract-With the new paradigm, Internet of Things, devices are now able to share services and resources generating higher level of services. However, the management and configuration of the smart devices are often troublesome, interrupting user's primary task. To automate the process of device collaboration, smart devices should be able to configure and manage themselves, self-identifying peer devices and their relationships. Hence, we proposed the concept of device sociality, which describes social relationship between devices. In device social network with device sociality, devices are able to detect peer devices and determine resources and services to share. To derive device sociality, we investigated social relationships between users and analyzed correlations between online social interactions and social relationships. Moreover, we also investigated social ties in terms of interaction direction, individual peculiarity, and network topology. In the experiment, we not only derived directional and individualized social affinity models, but also detected organizational structure and groups of the participants, confirming the potential of D2D collaboration.Index Terms-Device social, social relationship, social network, internet of things, communication, relationship model, tie strength.

show abstract

Section: Social Tie Analysismentioning

confidence: 99%

Estimating Social Tie Strength for Autonomous D2D Collaborations

Choi¹,

Kang²,

Jung³

et al. 2015

IJFCC

View full text Add to dashboard Cite

show abstract

“…We have reviewed several existing works [56,19] that identify the factors to be analysed. In order to move from theory to practice it is important to note that these factors are not easy to quantify and are limited by the social network's API extraction power.…”

Section: Social Knowledge Elicitation Modulesmentioning

confidence: 99%

“…The literature reviewed identifies these four factors as some of the major dimensions of predictive variables. With these dimensions as a guide, [56] identified 74 Facebook variables as potential predictors of tie strength. They presented a diagram showing percentages that indicate the predictive power of their top seven tie strength dimensions 9 and also the top three predictive variables for each dimension.…”

Section: Social Knowledge Elicitation Modulesmentioning

confidence: 99%

“…This change in the trust computation is due to the computed relevance of those factors (the weight in the trust computation of some of them was almost insignificant in [11]) and the extraction power that Facebook gives us (status was impossible to automatically extract reliably). 9 Note that [56]'s top four dimensions are the ones that [58] used as definition of tie strength and therefore the ones that we have adopted, predictive variables that [56] provided, we selected the ones that were more representative of each major dimension and which could also be extracted from users' Facebook profiles (as we have said before, we are limited to the elicitation power that Facebook grants us). The percentages that [56] presented for [58]'s four dimensions were:…”

Section: Social Knowledge Elicitation Modulesmentioning

confidence: 99%

“…Note that we compute as the literature has not resolved this issue, let alone specified how many discrete tie strength levels exist. 10 This dimension was not represented by [56]'s variables, from their variable definition we understood it as Profile Distance (13.8%) + Services (7.9%) 11 The weights presented in this equation are a proportion of the percentages of the top 4 variables presented by [56] (as [56]'s top 4 only sum 90,7%). 12 Note that the thresholds and specific values are different from the ones used in [10,11], as we have experimentally obtained them after analyzing average situations in the users' profiles that took part in our previous experiments.…”

Section: Social Knowledge Elicitation Modulesmentioning

confidence: 99%

See 2 more Smart Citations

Development of a group recommender application in a Social Network

Quijano-Sánchez

Díaz-Agudo

Recio-García

2014

Knowledge-Based Systems

View full text Add to dashboard Cite

In today's society, recommendations are becoming increasingly important. With the advent of the Social Web and the growing popularity of Social Networks, where users explicitly provide personal information and interact with others and the system, it is becoming clear that the key for the success of recommendations is to develop new strategies which focus on social recommendations leveraged by these new sources of knowledge. In our work, we focus on group recommender systems. These systems traditionally suffer from a number of shortcomings that hamper their effectiveness. In this paper we continue our research, that focuses on improving the overall quality of group recommendations through the addition of social knowledge to existing recommendation strategies. To do so, we use the information stored in Social Networks to elicit social factors following two approaches: the cognitive modeling approach, that studies how people's way of thinking predisposes their actions; and the social approach, that studies how people's relationships predispose their actions. We show the value of using models of social cognition extracted from Social Networks in group recommender systems through the instantiation of our model into a real-life Facebook movie recommender application.

show abstract

Investigating Political Polarization on Twitter: A Canadian Perspective

Gruzd¹,

Roy²

2014

Policy &Amp; Internet

240

165

View full text Add to dashboard Cite

This article investigates political polarization in social media by undertaking social network analysis of a sample of 5,918 tweets posted by 1,492 Twitter users during the 2011 Canadian Federal Election. On the one hand, we observed a clustering effect around shared political views among supporters of the same party in the Twitter communication network, suggesting that there are pockets of political polarization on Twitter. At the same time, there was evidence of cross‐ideological connections and exchanges, which may facilitate open, cross‐party, and cross‐ideological discourse, and ignite wider debate and learning as they are observed by nonaffiliated voters and the media at large. However, what appeared to be far less likely was any increased willingness or tendency for committed partisans to shift their allegiances as a result of their Twitter engagements, and we postulate that Twitter usage at present is likely to further embed partisan loyalties during electoral periods rather than loosen them; a dynamic that would seemingly contribute to political polarization.

show abstract

Predicting tie strength with social media

Cited by 1,065 publications

References 37 publications

Estimating Social Tie Strength for Autonomous D2D Collaborations

Estimating Social Tie Strength for Autonomous D2D Collaborations

Development of a group recommender application in a Social Network

Investigating Political Polarization on Twitter: A Canadian Perspective

Contact Info

Product

Resources

About