|
|
Data Mining in Social Networks
Raška, Jiří ; Očenášek, Pavel (referee) ; Bartík, Vladimír (advisor)
This thesis deals with knowledge discovery from social media. This thesis is focused on feature based opinion mining from user reviews. In theoretical part were described methods of opinion mining and natural language processing. Main parts of this thesis were design and implementation of library for opinion mining based on Stanford Parser and lexicon WordNet. For feature identi cation was used dependency grammar, implicit features were mined with method CoAR and opinions were classi ed with supervised algorithm. Finally were given experiments with implemented library and examples of usage.
|
|
|
On the Linguistic Structure of Emotional Meaning in Czech
Veselovská, Kateřina ; Hajičová, Eva (advisor) ; Petkevič, Vladimír (referee) ; Smrž, Pavel (referee)
Title: On the Linguistic Structure of Emotional Meaning in Czech Author: Mgr. Kateřina Veselovská Department: Institute of Formal and Applied Linguistics Supervisor: Prof. PhDr. Eva Hajičová, DrSc., Institute of Formal and Applied Linguistics Keywords: emotional meaning, linguistic structure, sentiment analysis, opinion mining, evaluative language Abstract: This thesis has two main goals. First, we provide an analysis of language means which together form an emotional meaning of written utterances in Czech. Sec- ond, we employ the findings concerning emotional language in computational applications. We provide a systematic overview of lexical, morphosyntactic, semantic and pragmatic aspects of emotional meaning in Czech utterances. Also, we propose two formal representations of emotional structures within the framework of the Prague Dependency Treebank and Construction Grammar. Regarding the computational applications, we focus on sentiment analysis, i.e. automatic extraction of emotions from text. We describe a creation of manually annotated emotional data resources in Czech and perform two main sentiment analysis tasks, polarity classification and opinion target identification on Czech data. In both of these tasks, we reach the state-of-the-art results.
|
|
|
On the Linguistic Structure of Emotional Meaning in Czech
Veselovská, Kateřina ; Hajičová, Eva (advisor) ; Petkevič, Vladimír (referee) ; Smrž, Pavel (referee)
Title: On the Linguistic Structure of Emotional Meaning in Czech Author: Mgr. Kateřina Veselovská Department: Institute of Formal and Applied Linguistics Supervisor: Prof. PhDr. Eva Hajičová, DrSc., Institute of Formal and Applied Linguistics Keywords: emotional meaning, linguistic structure, sentiment analysis, opinion mining, evaluative language Abstract: This thesis has two main goals. First, we provide an analysis of language means which together form an emotional meaning of written utterances in Czech. Sec- ond, we employ the findings concerning emotional language in computational applications. We provide a systematic overview of lexical, morphosyntactic, semantic and pragmatic aspects of emotional meaning in Czech utterances. Also, we propose two formal representations of emotional structures within the framework of the Prague Dependency Treebank and Construction Grammar. Regarding the computational applications, we focus on sentiment analysis, i.e. automatic extraction of emotions from text. We describe a creation of manually annotated emotional data resources in Czech and perform two main sentiment analysis tasks, polarity classification and opinion target identification on Czech data. In both of these tasks, we reach the state-of-the-art results.
|
|
|
Machine-Learning Methods in Natural Language Processing
Vodička, Jan ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
Bachelor's thesis deals with sentiment analysis using machine learning methods, mainly naive bayes classifier. Input text can be classified as positive or negative message. There are used several data sources for create of automatic annotated corpus - social network Twitter, price comparator Heureka, movie database ČSFD and restaurant portal Scuk. These sources are compared in terms of performance in assessing the sentiment. Consequently, the final training dataset is created and used at almost real-time Twitter sentiment analysis.
|
|
|
Data Mining in Social Networks
Raška, Jiří ; Očenášek, Pavel (referee) ; Bartík, Vladimír (advisor)
This thesis deals with knowledge discovery from social media. This thesis is focused on feature based opinion mining from user reviews. In theoretical part were described methods of opinion mining and natural language processing. Main parts of this thesis were design and implementation of library for opinion mining based on Stanford Parser and lexicon WordNet. For feature identi cation was used dependency grammar, implicit features were mined with method CoAR and opinions were classi ed with supervised algorithm. Finally were given experiments with implemented library and examples of usage.
|
|
|
Sentiment Analysis in the Czech Environment Network Twitter
Koller, Michael ; Kincl, Tomáš (advisor) ; Novák, Michal (referee)
Opinions are key influencers of human behaviours. Therefore, this bachelor thesis focuses on sentiment analysis, also called opinion mining, which is the one of the most active research areas in natural language processing and its application in business intelligence is more and more significant. Theoretical part thus describes the sentiment analysis problem, its advantages and applications. The main purpose of this thesis is to describe and appraise available tools for sentiment analysis in Czech conditions with focus on Twitter.
|
|
|
Virtual Image of the Czech Sports via Unstructured Data Analysis
Levý, Jan ; Jelínek, Ivan (advisor) ; Profousová, Lenka (referee)
Analysis of unstructured data from social media is an important and constantly growing part of information technologies' application in the marketing context. The aims of this bachelors' thesis include creating a trial platform for the analysis of un-structured data from Facebook, research and application of suitable methods and metrics for the analysis, summarizing the analysis' findings and visualisation of selected metrics by means of a dashboard. The thesis' structure corresponds to the methods used for metting the aims set and compo-ses of seven parts. The first part summarizes motives for social media analysis, deals with the approach to the topic in the contemporary scientific papers and discusses comercial tools that could be used for such analysis. The second part describes gathering of data with a crawler, setting the connection and getting the access rights to the data sources. The structure of downloaded documents and appropriate choice of data sources is also described in this part. The third part adresses the tools used for the analysis, namely Elas-ticsearch and Kibana. The fourth part defines possible questions that may be asked in the context of Czech sports image on Facebook. The fifth part identifies the metrics necessary for the questions assesment and describes corresponding data selection. The sixth part completes the analysis itself and summarizes its findnings. The seventh part describes Ki-bana's dashboard use for effective summarizing of selected metrics. The main bachelors' thesis contribution lies in the illustration of social media analysis pos-sibilities on the example of Czech sportsmen and Czech sports in general on Facebook. A crawler has been used to gather the data for the purpose of the analysis. The other em-ployed tools included Elasticsearch and Kibana, which have enabled the data selection and visualisation. The analytical approach consisted of four parts; definition of analytical que-stions, definition of methods and metrics to find answers to these questions, followed by the analysis itself and the summary of results. The following points belong to the analysis' findnings: identification of sportsman with the highest marketing potential, comparison of analysed sports according to the perceived image by fans and desgination of the pages with most interacting followers.
|
guest ::
