|
| |
|
|
Expert System for Decision-Making on Stock Markets Using Investor Sentiment
Janková, Zuzana ; Lenort, Radim (referee) ; Zinecker, Marek (referee) ; Chramcov, Bronislav (referee) ; Dostál, Petr (advisor)
The presented dissertation examines the potential of using the sentiment score extracted from textual data with historical stock index data to improve the performance of stock market prediction through the created model of the expert system. Given the large number of financial-related text documents published by both professional and amateur investors, not only on online social networks that could have an impact on real stock markets, but it is also crucial to analyze and in particular extract financial texts published by different users. investor sentiment. In this work, investor sentiment is obtained from online financial reports and contributions published on the financial social platform StockTwits. Sentiment scores are determined using a hybrid approach combining machine learning models with the teacher and neural networks, with multiple lexicons of positive and negative words used to classify sentiment polarity. The influence of sentiment score on the stock market through causality, cointegration and coherence is analyzed. The dissertation proposes a model of an expert system based on fuzzy logic methods. Fuzzy logic provides remarkable features when working with vague, inaccurate or unclear data and is able to deal with the chaotic environment of stock markets. In recent scientific studies, it has gained in popularity a higher level of fuzzy logic, which is referred to as type-2 fuzzy logic. Unlike the classic type-1 fuzzy logic, this higher type is able to integrate a certain level of uncertainty between the dual membership functions. However, this type of expert system is considerably neglected in the subject issue of stock market prediction using the extracted investor sentiment. For this reason, the dissertation examines the potential to use and the performance of type-2 fuzzy logic. Specifically, several type-2 fuzzy models are created. which are trained on historical stock index data and sentiment scores extracted from text data for the period 2018-2020. The created models are assessed to measure the prediction performance without sentiment and with the integration of investor sentiment. Subsequently, based on the created expert model, the investment strategy is determined, and its profitability is monitored. The prediction performance of fuzzy models is compared with the performance of several comparison models, including SVM, KNN, naive Bayes and others. It has been observed from experiments that fuzzy logic models are able to improve prediction by appropriate setting of membership and uncertainty functions contained in them and are able to compete with classical expert prediction models, which are standardly used in research studies. The created model should serve as a tool to support investment decisions for individual investors.
|
|
|
Advanced Songbook for Mobile Devices
Komárek, Ondřej ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
This Thesis describes all way from design and implementation to release and advertising of songbook application for Android operation system. The most important goal of the app is the ability to modify lyrics in such way, that they can be viewed flawlessly even on small screens of mobile devices. Application also features many other functions mostly useful for guitar players. User can download lyrics of song with chords directly from app and set up automatic scrolling with different speed for each part of the song. Thesis also describes other important aspects of application development, like user testing and final app release.
|
|
|
Process Automation in Design Sprint
Farkašová, Martina ; Hypský, Roman (referee) ; Kreslíková, Jitka (advisor)
The topic of the thesis is an automation of the processes that are considered an integral part of the Design sprint methodology. The proposed solution is based on the knowledge gained by participating in one of the design sprints at Kentico Software s.r.o. After analyzing the individual processes, the evaluation of customer feedback on the given prototype was chosen for automation. The created JavaScript solution performs text analysis of the feedback to help speed up its processing.
|
|
|
Speech Acts in Videogames
Šurýn, David ; Zmrzlá, Petra (referee) ; Sučková, Magda (advisor)
This bachelor thesis introduces a new approach of classifying interactions in video games based on the interaction between addressor and addressee and includes an analysis and comparison of speech acts in video games Life Is Strange and Call of Duty. This classification can be used to aid the process of analysis of speech acts in other video games and also assist game developers in the process of creating in-game interactions. To create such classification, the relation between the player and an interactable in-game element had to be prioritised. Then, the main classes of interactions in video games are introduced with each class containing specific types of speech acts. The analysis of speech acts in Life Is Strange and Call of Duty serves as an example of how this classification can be used and also shows many examples of how the game conveys information to the player. The list of interactions in this paper is not complete, but includes the most common and universal ones.
|
|
|
Text Analysis in Specialized Translation: Accuracy and Error Rate
Parobková, Alžbeta ; Marcoň, Petr (referee) ; Dohnal, Přemysl (advisor)
Práca sa zameriava na prieskum a aplikáciu metód textovej analýzy, strojového prekladu na vyhodnotenie kvality technických textov, preložených práve pomocou strojového automatického prekladu. Praktická časť využíva tieto metódy na implementáciu algoritmu pre identifikáciu a klasifikáciu chýb. Ďaľšou časťou praktickej časti je aj aplikácia a natrénovanie neurónového modelu pre korekciu týchto chýb. Porovnanie chybovosti a presnosti prekladu rôznymi prekladačmi je potom preukázané nie len kvalitatívne, ale aj kvantitatívne pomocou štandartných metrík.
|
|
| |
|
|
Reality Show Survivor: Competition, or Conflict?
Blažek, Jakub ; Hájek, Martin (advisor) ; Kolomoiets, Maksym (referee)
This thesis examines competition and conflict in the reality show Survivor. Its goal is to find out to what extent there are competitive and conflicting situations in the show, how they intertwine with each other, and how does this impact the final form of the show. In relation to this, the work also examines to what extent these interactions take place spontaneously, and to what extent they are constructed by the production of the show. It draws on academic literature on competition, conflict, and reality show, in order to backup the research with suitable theory. The research itself is done through the transcription of episodes of the reality show Survivor, which is then subjected to textual and contextual analysis. This enables subsequent interpretation of the findings. This interpretation shows that both competition and conflict have a central role in the show, and at the same time they are greatly interconnected. There is a lot of emphasis on competition in the show, which is especially noticeable during the challenges, where two tribes compete against each other. These challenges are bounded by rules, and they also offer a goal for which both tribes compete. To achieve this goal, it is neccessary to overcome the opponent's tribe. These situations are completely constructed by the production...
|
|
|
The Early Proses of Růžena Jesenská and its Critical Response.
TRÁVNÍČKOVÁ, Veronika
The bachelor thesis will present story and novel work by Czech writer Růžena Jesenská from 1900-1909 (the files specifically considered are: Novelly, 1909; Touha a láska, 1902; Mimo svět, 1909). In addition to it's own analysis of the relevant texts, we will also monitor the period reception of the works, i.e. the advantages or disadvantages attributed to the works of Jesenská and the literary contexts in which the works were placed at the time of their creation. With the support of period reviews and critics we will try to answer the question, whether the author fulfilled the contemporary idea of artistic or rather popular prose or whether there was a fusion of these two literary models.
|
|
|
Secondary school pupils' interpretation of the text Šťastná babyka by Daisy Mrázková
Šinkovičová, Patricie ; Laufková, Veronika (advisor) ; Komberec, Filip (referee)
The diploma thesis follows up the interpretation of a selected work of literature for children and youth by pupils of the secondary school. This thesis is divided into two parts - theoretical and empirical. The aim of the theoretical part is to anchor the concept of interpretation in the school environment based on the concept of reading literacy. The starting point for the second, empirical part of the work is the analysis of curricular documents anchoring the concept of interpretation (RVP ZV) in relation to the planned lesson, during which the research is carried out. The empirical part is conceived as a qualitative research that will answer specific research questions, including the interpretation of the main characters, the sound of the text and the naming of impressions from reading. The aim of the research is to cover and describe possible interpretations of the text Šťastná babyka by Daisy Mrázková from the point of view of the pupils of the secondary school. The research sample consists of eighteen pupils in the eighth grade of seondary school with extended language teaching. There are ten boys in the research sample, two of them with different mother language, and eight girls. The work Šťastná babyla by the author Daisy Mrázková was chosen with regard to the age of the pupils and their...
|
guest ::
