|
|
Estimation of Emotions from a Text
Dufková, Aneta ; Fajčík, Martin (referee) ; Szőke, Igor (advisor)
This thesis describes a process of estimation of emotions from a text using machine learning. The process starts with research of existing methods, continues with choosing a suitable method and experimenting. It uses several datasets, combines them and tests different techniques of text preprocessing. The result is a web interface which uses the pretrained model and allows to estimate emotions from Twitter posts.
|
|
|
Non-Supervised Sentiment Analysis
Karabelly, Jozef ; Landini, Federico Nicolás (referee) ; Fajčík, Martin (advisor)
Cieľom tejto práce je odprezentovať prehľad aktuálneho výskumu v oblasti analýzy sentimentu bez priameho učiteľa a identifikovať potenciálne smery výskumu. Okrem toho práca predstavuje novú účelovú funkciu na predtrénovanie, ktorá nevyžaduje priamy supervíziu. Rozšírenie modelu predstavenou účelovou funkciou, pridanie vrstvy neurónovej siete a následné samotné natrénovanie ukazujú sľubné výsledky. Rozšírený model naznačil schopnosť zakódovať abstraktné reprezentácie celkového sentimentu, emócií a sarkazmu. Pre účely použitia predstavenej účelovej funkcie bol nazbieraný vlastný dataset. Na základe experimentov vykonaných s rozšíreným modelom sú odprezentované možné smery výskumu a budúce vylepšenia.
|
|
|
Sharing Economy in the Context of Postmaterial Values: The Case of Accommodation Segment in Prague
Svobodová, Tereza ; Balon, Jan (advisor) ; Hájek, Martin (referee)
This master's thesis is about the success of sharing economy in the accommodation segment in Prague. The thesis is based on theories conceptualizing sharing economy as a result of social and value change, not only as technological one. Using online review data, the user experience of shared accommodation via Airbnb and traditional via Booking are compared. Analysis is conducted with focus on users' satisfied needs and fulfilled values. For processing the data, text mining techniques (topic modelling and sentiment analysis) were employed. The major result is that in Prague the models of sharing economy accommodation meets the growing need in society to fulfil post-material values in the market much better than the models of traditional accommodation (hotels, hostels, boarding houses). In their experiences, Airbnb users reflect social and emotional values more often, even though most sharing economy accommodations in Prague do not involve any physical sharing with the host. The thesis thus brings a unique perspective on the Airbnb phenomenon in the Czech context and contributes to the discussion of why the market share of the sharing economy in the accommodation segment in Prague has been growing, while traditional models stagnated.
|
|
|
Sentiment Analysis for the Field of Computer Games
Balajka, Pavel ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
The thesis deals with sentiment analysis extracted from opinions of users on social \mbox{networks}. It describes a general system that was created for presented purpose and specialised on the field of strategic computer games. In particular we unravel the problems of acquiring data from social networks, sentiment analysis and results presentation to the user. We mention particular ways of text processing e.g. tokenization and unnecessary word filtration, for purpose of more effective sentiment analysis and we mention machine learning methods e.g. Decision Trees and Naive Bayes, and their usage. Next we describe design of desired system and its implementation with chosen parts and methods. In the end we compare results of tests of sentiment analyzator done under various circumstances.
|
|
|
Využití syntaktické informace pro identifikaci hodnocených entit
Glončák, Vladan ; Hajič, Jan (advisor) ; Helcl, Jindřich (referee)
Opinion Target Extraction (OTE) is a well-established subtask of sentiment analysis. While detecting sentiment polarity is useful in itself, the ability to extract the targets of the opinions allows for more thorough decision making. For example, an owner of a restaurant needs to know whether the guests are complaining about the food, or the ambience, or any other aspect of their establishment, etc. Despite the lexical information being crucial for the task, syntactic structures have potential in being used to correctly decide among multiple candidate entities. Rules based on such structures have been used previously for the task. The objective of this thesis is to investigate, whether syntactic information influences the behavior of the state-of-the-art models such as recurrent neural networks for the OTE task. We did not find any substantial evidence to suggest that adding the syntactic information influences the behavior of the models.
|
|
|
Processing of User Reviews
Cihlářová, Dita ; Burget, Radek (referee) ; Bartík, Vladimír (advisor)
Very often, people buy goods on the Internet that they can not see and try. They therefore rely on reviews of other customers. However, there may be too many reviews for a human to handle them quickly and comfortably. The aim of this work is to offer an application that can recognize in Czech reviews what features of a product are most commented and whether the commentary is positive or negative. The results can save a lot of time for e-shop customers and provide interesting feedback to the manufacturers of the products.
|
|
|
Analysis of Social Media Content Discussing Czech Mobile Operators
Pavlů, Jan ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
The main topic of this thesis is sentiment analysis of posts obtained from a social networks. The posts are about czech mobile network operators. The essential part of implemented system is also data visualization. The sentiment analysis is done using machine learning techniques. Downloaded posts are cleaned, lemmatized and transformed to feature vectors. Stochastic Gradient Descent algorithm is used for classification. Analyzed data are visualized in charts and as the list of posts. The system provides tools for text categorization. The accuracy, precision, recall and F1 score of sentiment analysis is about 75%. The accuracy of post categorization is high (about 80%), but precision, recall and F1 score are low (about 30%). This is the reason why post categorization isn't automatically done. The benefit of the system it that it automatically collects data from different sources, analysis them and displays them. It also provides tools for manual change of sentiment/categories which can lead to better system characteristics with some help of users.
|
|
|
Sentiment Analysis of Czech Social Networks and Web Discussions on Retail Chains
Bolješik, Michal ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
The goal of this thesis is to design and implement a system that analyses data from the web mentioning Czech grocery chain stores. Implemented system is able to download such data automatically, perform sentiment analysis of the data, extract locations and chain stores' names from the data and index the data. The system also includes a user interface showing results of the analyses. The first part of the thesis surveys the state of the art in collecting data from web, sentiment analysis and indexing documents. A description of the discussed system's design and its implementation follows. The last part of the thesis evaluates implemented system
|
|
|
Rating of IT services through analysis of unstructured data
Kovykov, Maxim ; Vencovský, Filip (advisor) ; Bruckner, Tomáš (referee)
The main topic of this thesis is text mining and rating of services through summarization of unstructured text. The main goal is to describe a method for service rating. The method will be based on previous research. Described method will then be applied to real data. Another goal is to provide description of a toolset, necessary to fulfill set goals. This toolset will then be used to implement described method. The main contribution of this thesis is the implementation and application of the method on real data. The thesis is split into two parts: theory and practical application. Outputs of the practical applicaton are provided as an appendix.
|
|
|
The influence of YouTube on users
Houdková, Eliška ; Truhlář, Filip (advisor) ; Čupak, Daniel (referee)
This bachelor thesis examines the impact YouTube has on its viewers. The goal of this thesis is to determine, what kind of video content has the most emotional influence on the viewers. Firstly, the data for the analysis was taken from the comment section of selected videos, secondly the sentiment analysis was executed. This determined the emotional subtext of said comments. The theoretical part of this thesis defines YouTube in contrast to other social networks, describes general types of YouTube channels and sums up basic psychological knowledge related to media psychology. Results of this thesis can be used by YouTube content creators, who want to improve their content. The analysis can be used to further examine behaviour of social network users as well.
|
guest ::
