Predicting Community Evolution in Social Networks

Abstract

Nowadays, sustained development of different social media can be observed worldwide. One of the relevant research domains intensively explored recently is analysis of social communities existing in social media as well as prediction of their future evolution taking into account collected historical evolution chains. These evolution chains proposed in the paper contain group states in the previous time frames and its historical transitions that were identified using one out of two methods: Stable Group Changes Identification (SGCI) and Group Evolution Discovery (GED). Based on the observed evolution chains of various length, structural network features are extracted, validated and selected as well as used to learn classification models. The experimental studies were performed on three real datasets with different profile: DBLP, Facebook and Polish blogosphere. The process of group prediction was analysed with respect to different classifiers as well as various descriptive feature sets extracted from evolution chains of different length. The results revealed that, in general, the longer evolution chains the better predictive abilities of the classification models. However, chains of length 3 to 7 enabled the GED-based method to almost reach its maximum possible prediction quality. For SGCI, this value was at the level of 3-5 last periods. OPEN ACCESSEntropy 2015, 17 2

On community structure in complex networks: challenges and opportunities

“…Although this is somewhat a more restrictive setup compared to evolutionary clustering, the advantage of this approach is that it enables in principle the online clustering of networks [72][73][74][75]. Besides online community detection, the concept of forecasting the future events and changes in time dependent communities is also gaining considerable interest [76][77][78][79][80][81][82].…”

“…The basic idea is to build classifiers that can predict certain type of events based on various community features [79][80][81]. A detailed study of the problem together with a thorough testing of methods on multiple real datasets is presented in [82]. Stochastic immunization strategies focus on using information at the node level.…”

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

“…This work introduces the novel USMC method for efficient crawling of data from social network services by utilizing a wisdom of the crowd approach by allowing the users' interactions to guide the crawler to find content to crawl. The evaluation of the proposed USMC method, through social network analysis [8,29,30], shows that it can cover in excess of 80% of the social network by collecting merely 30% of the available posts on a page. The social networks constructed from the collected data are shown to have close to identical degree distribution already at as low sampling sizes as 20% compared to the whole page, which indicates that the social network structure of the 20% sample is nearly identical to the complete page.…”

Ekstraksi Knowledge tentang Penyebaran #Ratnamiliksiapa pada Jejaring Sosial (Twitter) menggunakan Social Network Analysis (SNA)

“…Social Network Analysis (SNA) merupakan salah satu solusi yang tepat untuk menganalisa relasi yang terjadi dengan adanya tagar #RatnaMilikSiapa pada jejaring sosial twitter. SNA merupakan sebuah metode yang berasal dari domain yang berbeda seperti teori grafik, sosiologi, fisika dan ilmu komputer untuk mempelajari tentang hubungan manusia dengan menggunakan teori graf, dengan pemanfaatan teori graf ini membuat SNA mampu memeriksa struktur dari hubungan sosial dalam suatu kelompok (Tsvetovat & Kouznetsov, 2011;Saganowski, 2015).…”