Facebook Profiles
Project Brief
Internet social networks may be an abundant source of opportunities giving space to the “parallel world” which can and, in many ways, does surpass the reality. People share data about almost every aspect of their lives, starting with giving opinions and comments on global problems and events, friends tagging at locations up to the point of multimedia personalized content. Therefore, decentralized mini-campaigns about educational, cultural, political and sports novelties could be conducted. In this project we have applied clustering algorithm to social network profiles with the aim of obtaining separate groups of people with different opinions about political views and parties.
Introduction
In particular, social media are increasingly used in political context. Potential voters share their impressions daily in the form of statuses about upcoming events and present state of affairs, their problems, political stances, agreements or disagreements with political activities, plans, and such like daily subjects. In order to meet the citizens’ needs, politicians and spin-doctors extract and analyze the information of interest from the available statuses. Twitter is favourite amongst politicians and other known personalities, and thus seems better for collecting and comparing public opinions. Facebook is the most used social network in Serbia, hence we focused our online political study on Facebook.
Facebook in Serbia
According to the last researches of Ministry of Trade, Tourism and Telecommunications in Republic of Serbia, 93.4% of Internet users aged 16 to 24 have a profile on the social networks (Facebook, Twitter). This project is based on Facebook audience, because most of the world’s population are friendly oriented according to this global Internet social network. Facebook Advertisement service presents potential reach of 3,600,000 people from Serbia for the promotion. If we are to believe the self-reported information from people in their Facebook profiles, about 45% of them are women and 55% are men. Information are only available for people aged 18 and older. The largest age group is currently form 18 to 24 with total of 1 440 000 users, followed by the users in the age form 25 to 34. Faculty (College) level educated people participate in about 66%, whilst high school students participate in about 32%. At the same time, percentage for single and married relationship status is 38% to 42%.
Methodology
Our research focuses on the political parties’ prevalence in the whole of territory of the Republic of Serbia. According to our figures, the total number of grabbed fanpages is 663925 and it corresponds to a total of 78758 profiles. Among these fanpages, 4095 are placed by their creators in the sphere of politics, while 771 pages have more than three likes. Profiles and fanpages are used for graph construction. Profiles represent graph nodes, while fanpages determine a measure for similarity between profiles, i.e. weight of the edges.
Last social research shows that people on the Internet social networks, such as Facebook, mark interactions with small number of friends compared to the total number of friends (about 8%), while the remaining ones are “passive”. Members of the mentioned minority have similar interests, common friends, and acquaintances from diverse events. We selected ten most numerous fanpages of each political party by searching keywords in the title related to their name, abbreviation and leaders.
Results
The algorithm was tested on real Facebook data, and we showed that similar<br>conclusions could be obtained in a faster way when compared to the research conducted by marketing agencies engaged for the same purpose and tasks. We determined four clear clusters for chosen political parties, so that we could distinguish them. However, there are a few small clusters (mixed) which cannot be explained, and this problem remains unsolved. Full scientific reference: B. Arsić, M. Bašić, P. Spalević, M. Ilić, M. Veinović. Facebook profiles clustering. 6th International Conference on Information Society and Technology (ICIST 2016), Serbia, 28 February – 2 March, 2016, pp. 154-158 (ISBN: 978-86-85525-16-2).