|
|
Virtual image of czech chain stores on social media
Krokosch, Michal ; Jelínek, Ivan (advisor) ; Oškera, Radek (referee)
This Bachelor thesis deals with the virtual image of chain stores in the Czech Republic, using their profiles on social networks, in this case on Facebook. The main goal of the thesis is to answer questions about these chain stores, which could be used, for example, by marketing departments of the stores. These not only include questions regarding recent cases in the media and their influence on the virtual image of chain stores, but also the long-term question of which of the stores is the most popular amongst users based on different metrics, such as the number of their fans and the analysis of sentiment. The thesis is divided into two parts, theoretical and practical. In the theoretical part, I clarify basic terms such as social network, why it is necessary to analyse them, but also what are chain stores and why they are so popular among customers. The practical part includes an explanation of the methods used in downloading data from Facebook and in the following analysis. The results of the analysis are also presented here. This Bachelor thesis could be beneficial to chain stores, which could adjust their strategy of approaching customers accordingly, or to customers themselves, who could change their preference for a chain store because of its presentation on social media.
|
|
|
Analysis of Czech football from the content of social networks
Zálepa, Martin ; Jelínek, Ivan (advisor) ; Oškera, Radek (referee)
The main aim of this report is to analyse the Czech football scene using the unstructured data from ever evolving social media platform Facebook. The objectives are to identify key concepts using the Czech football social community, dis-covering the most popular club, understanding the buzz and reactions on independent sport portals and identifying the relation between social sentiment and the actual football club performance. These objectives are met using defined methods including collection, analysis and evaluation of the data, applying the key data metrics and relevant literature research, as well as graphical visualisation of the results. This report consists of five chapters split into theoretical and practical part. The first three chapters, the theoretical part, are focusing on the explanation of the social media in general, using the literature research and online analytical tools, and introduction of the Czech foot-ball scene from both commercial and marketing standpoint. The last chapter describes the methods applied and outlines the data architecture used for the analysis. The practical part includes a definition of the key metrics that are initially defined as business assumptions and consequently applied and transformed into the basis of this analysis. The last chapter of the practical part forms the actual data analysis and its evaluation as well as visualisation of the partial results. The main purpose of this report is to demonstrate the benefits of analysing unstructured data from social media platforms that can be connected and downloaded using the tools such as Elasticsearch and Kibana, that enable to discover, filter and visualise the data. Gaining an insight into social media and visualisation of the data is also beneficial to spon-sors and football clubs as it can maximise the power of their marketing as well as enable them to understand the reputation and consumer perception.
|
|
|
Options of automated categorization of contracts
Bereš, Miroslav ; Jelínek, Ivan (advisor) ; Oškera, Radek (referee)
My bachelor thesis is focused on automatic categorization. The main goal is to examine actual approaches in automatic categorization, propose methodology for an experiment and perform the experiment. The experiment is done in order to measure success rate of automatic categorization with use of machine learning. It is performed on contracts obtained from public administration's web pages. The bachelor is divided into two parts, theoretical part and the experiment. First one focuses on analyzing theory which explains the subject matter, there are also described current approaches in automatic categorization. Second part describes methodology proposal of the experiment and performing of the experiment. During the process of the experiment, there are created models that are applied on control group. The experiment's outputs are categorized documents. These documents are used to monitor the success rate of automatic categorization. In order to measure the success rate, there is software called Apache OpenNLP used in this experiment. The theoretical part and proposal of the methodology are written based on studying foreign professional literature, mostly obtained from electronic and information sources.
|
guest ::
