• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
For visually-impairedUser profile (HSE staff only)SearchMenu

Social Media Link-prediction for Targeted Content Propagation Towards a Creative Economy

Student: Sangam kumar Singh

Supervisor: Alexander Gromoff

Faculty: Graduate School of Business

Educational Programme: Big Data Systems (Master)

Year of Graduation: 2020

Social Network as an area is of immense interest to the researchers and business. With the ever-growing number of user on the social media platform, and increasing requirement to focus on the user group, which can potentially form a community is of utmost importance. In this research, the author hypothesized that the personalized online social media behaviour could be considered for link-prediction signifying whether an individual is connected or has similar interest/behaviour or preference. Thus, identifying individuals with the same preference or interest can help significantly towards Innovative Business Intelligence (IBI) and targeted content penetration across the large scale online social media. This, as a result, can help to accomplish the most effective mobile or internet marketing for business purposes though significant virality features. However, considering it as the motive in this research at first, a large scale online user information was obtained, which comprised different features, including corresponding social behavioural as well as topological traits. Such amalgamation of the different features enabled retrieving sufficient information about an individual to assess its preferences, intend, etc. Thus, with obtained (personalized) features, this research targeted to estimate correlation or association between the different individuals. Considering the above-stated approach in this research, a novel and first of its kind approach was developed which focused on exploiting advance software computing technologies, including machine learning to yield optimal social media link-prediction. In this approach, at first, a large scale online social media data was taken into consideration which encompassed each user’s topological as well as behavioural features. Thus, with the obtained features at first different essential feature set were obtained. This, as a result, can help to get an optimal solution towards content virality over social media for better internet marketing. Keywords: socio-technical, virality, internet, social media, social media analytics, computational social science, marketing applications.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses