Leveraging Social Interactions to Suggest Friends

Bródka

Boldt

et al. 2017

Entropy

Self Cite

Abstract:With the growing use of popular social media services like Facebook and Twitter it is challenging to collect all content from the networks without access to the core infrastructure or paying for it. Thus, if all content cannot be collected one must consider which data are of most importance. In this work we present a novel User-guided Social Media Crawling method (USMC) that is able to collect data from social media, utilizing the wisdom of the crowd to decide the order in which user generated content should be collected to cover as many user interactions as possible. USMC is validated by crawling 160 public Facebook pages, containing content from 368 million users including 1.3 billion interactions, and it is compared with two other crawling methods. The results show that it is possible to cover approximately 75% of the interactions on a Facebook page by sampling just 20% of its posts, and at the same time reduce the crawling time by 53%. In addition, the social network constructed from the 20% sample contains more than 75% of the users and edges compared to the social network created from all posts, and it has similar degree distribution.

Section: Motivationmentioning

confidence: 99%

Do We Really Need to Catch Them All? A New User-Guided Social Media Crawling Method

Bródka

Boldt

et al. 2017

Entropy

Self Cite

“…Like in many different areas, scientists struggle to predict the future of online social network. The main focus in social network area is on link prediction [16] but different teams around the world work also on: (i) popularity prediction in social media based on comment mining [12], (ii) personality prediction for micro blog Users [29], (iii) churn prediction and its influence on the network [4,22], (iv) community evolution prediction [7,23], (v) using social media to predict real-world outcomes [3], (vi) predicting information cascade on social media [11], (vii) users features prediction using relational learning [14,15], (viii) predicting patterns of diffusion processes in social network [13], (ix) predicting friendship intensity [2,20], (x) affiliation recommendations [25,26], and many others.…”

Section: Related Workmentioning

confidence: 99%

Predicting User Participation in Social Media

Advances in Network Science

Borg

Johnson

et al. 2016

Self Cite

Abstract. Online social networking services like Facebook provides a popular way for users to participate in different communication groups and discuss relevant topics with each other. While users tend to have an impact on each other, it is important to better understand and analyze users behavior in specific online groups. For social networking sites it is of interest to know if a topic will be interesting for users or not. Therefore, this study examines the prediction of user participation in online social networks discussions, in which we argue that it is possible to predict user participation in a public group using common machine learning techniques. We are predicting user participation based on association rules built with respect to user activeness of current posts. In total, we have crawled and extracted 2,443 active users interacting on 610 posts with over 14,117 comments on Facebook. The results show that the proposed approach has a high level of accuracy and the systematic study clearly depicts the possibility to predict user participation in social networking sites.

“…Since we are dependent on depth, we are aiming on applications built for leveraging social interaction networks, such as Friend Suggestion [8]. Hence SINCE is implemented as a deep interaction crawler.…”

Section: Related Workmentioning

confidence: 99%

“…SINCE makes the social information around posts easily and thoroughly accessible, which is necessary in order to create SINs and build applications such as Friend Suggestion [8] which are dependent on the complete set of interactions between users.…”

Section: Introductionmentioning

confidence: 99%

Crawling Online Social Networks

2015 Second European Network Intelligence Conference

Nia

Boldt

et al. 2015

Self Cite

Abstract-Researchers put in tremendous amount of time and effort in order to crawl the information from online social networks. With the variety and the vast amount of information shared on online social networks today, different crawlers have been designed to capture several types of information. We have developed a novel crawler called SINCE. This crawler differs significantly from other existing crawlers in terms of efficiency and crawling depth. We are getting all interactions related to every single post. In addition, are we able to understand interaction dynamics, enabling support for making informed decisions on what content to re-crawl in order to get the most recent snapshot of interactions. Finally we evaluate our crawler against other existing crawlers in terms of completeness and efficiency. Over the last years we have crawled public communities on Facebook, resulting in over 500 million unique Facebook users, 50 million posts, 500 million comments and over 6 billion likes.